{ "generated_at": "2026-11-02T07:13:51Z", "evaluator": "anthropic/claude-haiku-5-5", "dimensions": [ "accuracy", "completeness", "clarity", "domain_expertise", "helpfulness" ], "categories": [ { "name": "AI", "prompts": 1 }, { "name": "Classification - Few shot", "prompts": 10 }, { "name": "Classification - Zero shot", "prompts": 10 }, { "name": "Creative", "prompts": 1 }, { "name": "Education", "prompts": 2 }, { "name": "Factography", "prompts": 2 }, { "name": "Health", "prompts": 1 }, { "name": "HR", "prompts": 2 }, { "name": "Linux", "prompts": 1 }, { "name": "LLM", "prompts": 2 }, { "name": "Logic", "prompts": 1 }, { "name": "Philosophy", "prompts": 1 }, { "name": "Polski", "prompts": 3 }, { "name": "Programming", "prompts": 33 }, { "name": "RAG", "prompts": 2 }, { "name": "Reasoning", "prompts": 1 }, { "name": "Role prompting", "prompts": 6 }, { "name": "Structured output", "prompts": 11 }, { "name": "Telco", "prompts": 8 }, { "name": "Terminal", "prompts": 10 } ], "models": [ { "name": "alibayram/smollm3:latest", "family": "smollm3", "params_b": 3.1, "quantization": "Q4_K_M", "context_length": 65536, "size_bytes": 1915305999, "size_estimated": false, "installed": true, "min_memory_gb": 3.4, "overall": 2.823, "rated": 71, "failed": 17, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 3.18, "n": 10 }, "Classification - Zero shot": { "avg": 2.62, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "HR": { "avg": 2.6, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 3.4, "n": 2 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Programming": { "avg": 2.305, "n": 19 }, "Role prompting": { "avg": 1.333, "n": 6 }, "Structured output": { "avg": 3.4, "n": 10 }, "Telco": { "avg": 3.8, "n": 6 } }, "dimensions": { "accuracy": 2.789, "completeness": 2.887, "clarity": 3.352, "domain_expertise": 2.662, "helpfulness": 2.437 }, "tokens_per_second": 223.7 }, { "name": "command-r7b:latest", "family": "cohere2", "params_b": 8.0, "quantization": "Q4_K_M", "context_length": 8192, "size_bytes": 5057031198, "size_estimated": false, "installed": true, "min_memory_gb": 6.6, "overall": 3.277, "rated": 78, "failed": 10, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 3.88, "n": 10 }, "Classification - Zero shot": { "avg": 4.2, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.2, "n": 2 }, "HR": { "avg": 2.8, "n": 1 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 1.4, "n": 3 }, "Programming": { "avg": 2.591, "n": 22 }, "RAG": { "avg": 3.4, "n": 1 }, "Reasoning": { "avg": 2.8, "n": 1 }, "Role prompting": { "avg": 2.1, "n": 6 }, "Structured output": { "avg": 3.927, "n": 11 }, "Telco": { "avg": 4.0, "n": 5 } }, "dimensions": { "accuracy": 3.154, "completeness": 3.359, "clarity": 4.0, "domain_expertise": 2.885, "helpfulness": 2.987 }, "tokens_per_second": 118.2 }, { "name": "deepseek-r1:32b", "family": "qwen2", "params_b": 32.8, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 20090000000, "size_estimated": true, "installed": false, "min_memory_gb": 21.6, "overall": 3.361, "rated": 83, "failed": 5, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 3.74, "n": 10 }, "Classification - Zero shot": { "avg": 3.98, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 2.9, "n": 2 }, "Factography": { "avg": 2.2, "n": 1 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 2.6, "n": 2 }, "Linux": { "avg": 3.0, "n": 1 }, "Polski": { "avg": 1.533, "n": 3 }, "Programming": { "avg": 2.964, "n": 22 }, "RAG": { "avg": 2.8, "n": 2 }, "Role prompting": { "avg": 3.333, "n": 6 }, "Structured output": { "avg": 3.673, "n": 11 }, "Telco": { "avg": 4.1, "n": 8 } }, "dimensions": { "accuracy": 3.675, "completeness": 3.398, "clarity": 3.349, "domain_expertise": 3.301, "helpfulness": 3.084 }, "tokens_per_second": 6.9 }, { "name": "deepseek-r1:8b", "family": "qwen3", "params_b": 8.2, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 5022500000, "size_estimated": true, "installed": false, "min_memory_gb": 6.5, "overall": 3.257, "rated": 77, "failed": 11, "categories": { "AI": { "avg": 3.2, "n": 1 }, "Classification - Few shot": { "avg": 4.44, "n": 10 }, "Classification - Zero shot": { "avg": 4.22, "n": 10 }, "Creative": { "avg": 3.2, "n": 1 }, "Education": { "avg": 2.8, "n": 2 }, "HR": { "avg": 2.4, "n": 2 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 3.0, "n": 2 }, "Polski": { "avg": 2.333, "n": 3 }, "Programming": { "avg": 2.4, "n": 20 }, "RAG": { "avg": 2.3, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 2.3, "n": 6 }, "Structured output": { "avg": 3.982, "n": 11 }, "Telco": { "avg": 3.4, "n": 5 } }, "dimensions": { "accuracy": 3.156, "completeness": 3.468, "clarity": 3.61, "domain_expertise": 2.935, "helpfulness": 3.117 }, "tokens_per_second": 105.4 }, { "name": "devstral-small-2:24b", "family": "mistral3", "params_b": 24.0, "quantization": "Q4_K_M", "context_length": 393216, "size_bytes": 14700000000, "size_estimated": true, "installed": false, "min_memory_gb": 16.2, "overall": 3.735, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.18, "n": 10 }, "Classification - Zero shot": { "avg": 3.9, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "Factography": { "avg": 2.4, "n": 1 }, "HR": { "avg": 3.5, "n": 2 }, "Health": { "avg": 4.2, "n": 1 }, "LLM": { "avg": 3.9, "n": 2 }, "Linux": { "avg": 3.4, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.133, "n": 3 }, "Programming": { "avg": 3.365, "n": 23 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 2.0, "n": 1 }, "Role prompting": { "avg": 3.5, "n": 6 }, "Structured output": { "avg": 4.2, "n": 11 }, "Telco": { "avg": 4.4, "n": 8 } }, "dimensions": { "accuracy": 3.616, "completeness": 3.721, "clarity": 4.5, "domain_expertise": 3.337, "helpfulness": 3.5 }, "tokens_per_second": 50.2 }, { "name": "exaone3.5:7.8b", "family": "exaone", "params_b": 7.8, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 4770664857, "size_estimated": false, "installed": true, "min_memory_gb": 6.3, "overall": 3.132, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 3.04, "n": 10 }, "Classification - Zero shot": { "avg": 4.24, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "HR": { "avg": 2.1, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.9, "n": 2 }, "Linux": { "avg": 2.0, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.2, "n": 3 }, "Programming": { "avg": 2.817, "n": 23 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 1.4, "n": 1 }, "Role prompting": { "avg": 1.633, "n": 6 }, "Structured output": { "avg": 3.655, "n": 11 }, "Telco": { "avg": 3.375, "n": 8 } }, "dimensions": { "accuracy": 2.965, "completeness": 3.212, "clarity": 3.894, "domain_expertise": 2.741, "helpfulness": 2.847 }, "tokens_per_second": 137.1 }, { "name": "flint:latest", "family": null, "params_b": null, "quantization": null, "context_length": null, "size_bytes": null, "size_estimated": true, "installed": false, "min_memory_gb": null, "overall": 3.759, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.52, "n": 10 }, "Classification - Zero shot": { "avg": 4.46, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 4.0, "n": 2 }, "Factography": { "avg": 1.6, "n": 2 }, "HR": { "avg": 3.2, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 4.4, "n": 2 }, "Linux": { "avg": 3.4, "n": 1 }, "Logic": { "avg": 1.4, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 3.267, "n": 3 }, "Programming": { "avg": 3.409, "n": 23 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 2.933, "n": 6 }, "Structured output": { "avg": 4.309, "n": 11 }, "Telco": { "avg": 3.55, "n": 8 } }, "dimensions": { "accuracy": 3.739, "completeness": 3.773, "clarity": 4.386, "domain_expertise": 3.341, "helpfulness": 3.568 }, "tokens_per_second": 94.3 }, { "name": "gemma2:2b", "family": "gemma2", "params_b": 2.6, "quantization": "Q4_0", "context_length": 8192, "size_bytes": 1629518495, "size_estimated": false, "installed": true, "min_memory_gb": 3.1, "overall": 2.708, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 3.94, "n": 10 }, "Classification - Zero shot": { "avg": 2.84, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "HR": { "avg": 2.2, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.2, "n": 2 }, "Linux": { "avg": 1.4, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 1.667, "n": 3 }, "Programming": { "avg": 1.913, "n": 23 }, "RAG": { "avg": 3.0, "n": 2 }, "Reasoning": { "avg": 2.0, "n": 1 }, "Role prompting": { "avg": 2.167, "n": 6 }, "Structured output": { "avg": 3.218, "n": 11 }, "Telco": { "avg": 2.925, "n": 8 } }, "dimensions": { "accuracy": 2.482, "completeness": 2.671, "clarity": 3.624, "domain_expertise": 2.388, "helpfulness": 2.376 }, "tokens_per_second": 241.0 }, { "name": "gemma2:9b", "family": "gemma2", "params_b": 9.2, "quantization": "Q4_0", "context_length": 8192, "size_bytes": 5175000000, "size_estimated": true, "installed": false, "min_memory_gb": 6.7, "overall": 3.635, "rated": 81, "failed": 7, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 4.72, "n": 10 }, "Classification - Zero shot": { "avg": 4.7, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "HR": { "avg": 3.1, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 3.7, "n": 2 }, "Linux": { "avg": 2.8, "n": 1 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Polski": { "avg": 1.8, "n": 3 }, "Programming": { "avg": 2.713, "n": 23 }, "RAG": { "avg": 3.4, "n": 1 }, "Role prompting": { "avg": 2.9, "n": 6 }, "Structured output": { "avg": 4.327, "n": 11 }, "Telco": { "avg": 4.167, "n": 6 } }, "dimensions": { "accuracy": 3.543, "completeness": 3.568, "clarity": 4.42, "domain_expertise": 3.198, "helpfulness": 3.457 }, "tokens_per_second": 98.9 }, { "name": "gemma2:latest", "family": "gemma2", "params_b": 9.2, "quantization": "Q4_0", "context_length": 8192, "size_bytes": 5175000000, "size_estimated": true, "installed": false, "min_memory_gb": 6.7, "overall": 3.683, "rated": 82, "failed": 6, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 4.72, "n": 10 }, "Classification - Zero shot": { "avg": 4.68, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "HR": { "avg": 3.5, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Linux": { "avg": 3.2, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.0, "n": 3 }, "Programming": { "avg": 2.87, "n": 23 }, "RAG": { "avg": 3.2, "n": 1 }, "Role prompting": { "avg": 2.967, "n": 6 }, "Structured output": { "avg": 4.109, "n": 11 }, "Telco": { "avg": 4.314, "n": 7 } }, "dimensions": { "accuracy": 3.646, "completeness": 3.585, "clarity": 4.439, "domain_expertise": 3.317, "helpfulness": 3.427 }, "tokens_per_second": 61.0 }, { "name": "gemma3:12b", "family": "gemma3", "params_b": 12.2, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 8149190253, "size_estimated": false, "installed": true, "min_memory_gb": 9.6, "overall": 3.829, "rated": 83, "failed": 5, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.7, "n": 10 }, "Classification - Zero shot": { "avg": 4.64, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "Factography": { "avg": 2.0, "n": 1 }, "HR": { "avg": 3.8, "n": 2 }, "Health": { "avg": 4.2, "n": 1 }, "LLM": { "avg": 4.1, "n": 2 }, "Linux": { "avg": 2.8, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 3.6, "n": 3 }, "Programming": { "avg": 2.939, "n": 23 }, "RAG": { "avg": 3.8, "n": 2 }, "Role prompting": { "avg": 3.667, "n": 6 }, "Structured output": { "avg": 4.145, "n": 11 }, "Telco": { "avg": 4.433, "n": 6 } }, "dimensions": { "accuracy": 3.807, "completeness": 3.831, "clarity": 4.361, "domain_expertise": 3.446, "helpfulness": 3.687 }, "tokens_per_second": 68.3 }, { "name": "gemma3:1b", "family": "gemma3", "params_b": 1.0, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 815319791, "size_estimated": false, "installed": true, "min_memory_gb": 2.3, "overall": 2.48, "rated": 75, "failed": 33, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.7, "n": 6 }, "Classification - Zero shot": { "avg": 4.75, "n": 4 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.8, "n": 1 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 4.4, "n": 1 }, "Programming": { "avg": 1.738, "n": 29 }, "RAG": { "avg": 2.6, "n": 2 }, "Role prompting": { "avg": 1.633, "n": 6 }, "Structured output": { "avg": 3.02, "n": 10 }, "Telco": { "avg": 4.133, "n": 3 }, "Terminal": { "avg": 1.12, "n": 10 } }, "dimensions": { "accuracy": 2.373, "completeness": 2.453, "clarity": 3.04, "domain_expertise": 2.2, "helpfulness": 2.333 }, "tokens_per_second": 270.1 }, { "name": "gemma3:27b", "family": "gemma3", "params_b": 27.4, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 17396936941, "size_estimated": false, "installed": true, "min_memory_gb": 18.9, "overall": 3.911, "rated": 83, "failed": 5, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.64, "n": 10 }, "Classification - Zero shot": { "avg": 4.7, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.9, "n": 2 }, "Factography": { "avg": 1.4, "n": 1 }, "HR": { "avg": 3.8, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 4.0, "n": 2 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Polski": { "avg": 3.333, "n": 3 }, "Programming": { "avg": 3.182, "n": 22 }, "RAG": { "avg": 3.9, "n": 2 }, "Reasoning": { "avg": 2.0, "n": 1 }, "Role prompting": { "avg": 3.8, "n": 6 }, "Structured output": { "avg": 4.291, "n": 11 }, "Telco": { "avg": 4.371, "n": 7 } }, "dimensions": { "accuracy": 3.88, "completeness": 3.916, "clarity": 4.518, "domain_expertise": 3.482, "helpfulness": 3.759 }, "tokens_per_second": 31.8 }, { "name": "gemma3:4b", "family": "gemma3", "params_b": 4.3, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 3338801804, "size_estimated": false, "installed": true, "min_memory_gb": 4.8, "overall": 3.67, "rated": 77, "failed": 11, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.68, "n": 10 }, "Classification - Zero shot": { "avg": 4.72, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.9, "n": 2 }, "HR": { "avg": 3.2, "n": 1 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 3.7, "n": 2 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 2.733, "n": 3 }, "Programming": { "avg": 2.682, "n": 22 }, "RAG": { "avg": 2.9, "n": 2 }, "Role prompting": { "avg": 3.267, "n": 6 }, "Structured output": { "avg": 4.127, "n": 11 }, "Telco": { "avg": 4.2, "n": 4 } }, "dimensions": { "accuracy": 3.584, "completeness": 3.662, "clarity": 4.312, "domain_expertise": 3.26, "helpfulness": 3.532 }, "tokens_per_second": 155.6 }, { "name": "gemma3:latest", "family": "gemma3", "params_b": 4.3, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 3338801804, "size_estimated": false, "installed": true, "min_memory_gb": 4.8, "overall": 3.489, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.6, "n": 10 }, "Classification - Zero shot": { "avg": 4.66, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.9, "n": 2 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 4.2, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 2.733, "n": 3 }, "Programming": { "avg": 2.6, "n": 23 }, "RAG": { "avg": 3.8, "n": 2 }, "Reasoning": { "avg": 1.8, "n": 1 }, "Role prompting": { "avg": 3.067, "n": 6 }, "Structured output": { "avg": 3.964, "n": 11 }, "Telco": { "avg": 3.05, "n": 8 } }, "dimensions": { "accuracy": 3.353, "completeness": 3.518, "clarity": 4.235, "domain_expertise": 3.094, "helpfulness": 3.247 }, "tokens_per_second": 77.3 }, { "name": "gemma3n:e2b", "family": "gemma3n", "params_b": 4.5, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 5621616562, "size_estimated": false, "installed": true, "min_memory_gb": 7.1, "overall": 3.352, "rated": 84, "failed": 4, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.44, "n": 10 }, "Classification - Zero shot": { "avg": 4.56, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 4.2, "n": 1 }, "LLM": { "avg": 3.9, "n": 2 }, "Linux": { "avg": 2.0, "n": 1 }, "Philosophy": { "avg": 3.6, "n": 1 }, "Polski": { "avg": 3.067, "n": 3 }, "Programming": { "avg": 2.348, "n": 23 }, "RAG": { "avg": 3.0, "n": 2 }, "Reasoning": { "avg": 2.0, "n": 1 }, "Role prompting": { "avg": 3.1, "n": 6 }, "Structured output": { "avg": 3.82, "n": 10 }, "Telco": { "avg": 3.025, "n": 8 } }, "dimensions": { "accuracy": 3.143, "completeness": 3.417, "clarity": 4.083, "domain_expertise": 2.929, "helpfulness": 3.19 }, "tokens_per_second": 57.2 }, { "name": "gemma3n:latest", "family": "gemma3n", "params_b": 6.9, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 7547589116, "size_estimated": false, "installed": true, "min_memory_gb": 9.0, "overall": 3.494, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.44, "n": 10 }, "Classification - Zero shot": { "avg": 4.44, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "HR": { "avg": 3.5, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 4.0, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 3.6, "n": 3 }, "Programming": { "avg": 2.661, "n": 23 }, "RAG": { "avg": 3.1, "n": 2 }, "Reasoning": { "avg": 1.8, "n": 1 }, "Role prompting": { "avg": 3.567, "n": 6 }, "Structured output": { "avg": 3.582, "n": 11 }, "Telco": { "avg": 3.325, "n": 8 } }, "dimensions": { "accuracy": 3.353, "completeness": 3.612, "clarity": 4.153, "domain_expertise": 3.094, "helpfulness": 3.259 }, "tokens_per_second": 29.3 }, { "name": "gemma4:12b", "family": "gemma4", "params_b": 11.9, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 7556508396, "size_estimated": false, "installed": true, "min_memory_gb": 9.1, "overall": 3.88, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.66, "n": 10 }, "Classification - Zero shot": { "avg": 4.52, "n": 10 }, "Creative": { "avg": 4.4, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 2.1, "n": 2 }, "HR": { "avg": 3.9, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 2.7, "n": 2 }, "Linux": { "avg": 3.2, "n": 1 }, "Logic": { "avg": 1.8, "n": 1 }, "Philosophy": { "avg": 2.8, "n": 1 }, "Polski": { "avg": 4.067, "n": 3 }, "Programming": { "avg": 3.479, "n": 33 }, "RAG": { "avg": 4.0, "n": 2 }, "Reasoning": { "avg": 4.6, "n": 1 }, "Role prompting": { "avg": 3.867, "n": 6 }, "Structured output": { "avg": 4.418, "n": 11 }, "Telco": { "avg": 4.625, "n": 8 }, "Terminal": { "avg": 3.34, "n": 10 } }, "dimensions": { "accuracy": 3.75, "completeness": 3.889, "clarity": 4.528, "domain_expertise": 3.528, "helpfulness": 3.704 }, "tokens_per_second": 66.5 }, { "name": "gemma4:26b", "family": "gemma4", "params_b": 25.8, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 17987581215, "size_estimated": false, "installed": true, "min_memory_gb": 19.5, "overall": 3.928, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.76, "n": 10 }, "Classification - Zero shot": { "avg": 4.72, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.9, "n": 2 }, "Factography": { "avg": 2.8, "n": 2 }, "HR": { "avg": 4.3, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 4.4, "n": 2 }, "Linux": { "avg": 4.0, "n": 1 }, "Logic": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 1.8, "n": 3 }, "Programming": { "avg": 3.461, "n": 33 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 4.6, "n": 1 }, "Role prompting": { "avg": 3.9, "n": 6 }, "Structured output": { "avg": 4.164, "n": 11 }, "Telco": { "avg": 4.725, "n": 8 }, "Terminal": { "avg": 3.74, "n": 10 } }, "dimensions": { "accuracy": 3.778, "completeness": 4.009, "clarity": 4.454, "domain_expertise": 3.639, "helpfulness": 3.778 }, "tokens_per_second": 113.3 }, { "name": "gemma4:31b", "family": "gemma4", "params_b": 31.3, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 19868981791, "size_estimated": false, "installed": true, "min_memory_gb": 21.4, "overall": 4.079, "rated": 107, "failed": 1, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.68, "n": 10 }, "Classification - Zero shot": { "avg": 4.64, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 2.2, "n": 1 }, "HR": { "avg": 3.7, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 4.3, "n": 2 }, "Linux": { "avg": 4.2, "n": 1 }, "Logic": { "avg": 4.2, "n": 1 }, "Philosophy": { "avg": 4.6, "n": 1 }, "Polski": { "avg": 1.667, "n": 3 }, "Programming": { "avg": 3.842, "n": 33 }, "RAG": { "avg": 4.1, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 4.0, "n": 6 }, "Structured output": { "avg": 3.982, "n": 11 }, "Telco": { "avg": 4.825, "n": 8 }, "Terminal": { "avg": 4.12, "n": 10 } }, "dimensions": { "accuracy": 4.047, "completeness": 4.065, "clarity": 4.561, "domain_expertise": 3.738, "helpfulness": 3.981 }, "tokens_per_second": 31.5 }, { "name": "gemma4:e2b", "family": "gemma4", "params_b": 5.1, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 7162405886, "size_estimated": false, "installed": true, "min_memory_gb": 8.7, "overall": 3.518, "rated": 107, "failed": 1, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.52, "n": 10 }, "Classification - Zero shot": { "avg": 4.58, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 1.4, "n": 1 }, "HR": { "avg": 4.1, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 4.3, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Logic": { "avg": 2.0, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.0, "n": 3 }, "Programming": { "avg": 2.758, "n": 33 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 1.8, "n": 1 }, "Role prompting": { "avg": 3.833, "n": 6 }, "Structured output": { "avg": 4.455, "n": 11 }, "Telco": { "avg": 4.225, "n": 8 }, "Terminal": { "avg": 2.5, "n": 10 } }, "dimensions": { "accuracy": 3.299, "completeness": 3.486, "clarity": 4.29, "domain_expertise": 3.234, "helpfulness": 3.299 }, "tokens_per_second": 165.7 }, { "name": "gemma4:e4b", "family": "gemma4", "params_b": 8.0, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 9608350718, "size_estimated": false, "installed": true, "min_memory_gb": 11.1, "overall": 3.643, "rated": 107, "failed": 1, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.66, "n": 10 }, "Classification - Zero shot": { "avg": 4.66, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "Factography": { "avg": 1.2, "n": 1 }, "HR": { "avg": 4.0, "n": 2 }, "Health": { "avg": 3.8, "n": 1 }, "LLM": { "avg": 4.1, "n": 2 }, "Linux": { "avg": 4.4, "n": 1 }, "Logic": { "avg": 2.0, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 2.067, "n": 3 }, "Programming": { "avg": 3.103, "n": 33 }, "RAG": { "avg": 3.8, "n": 2 }, "Reasoning": { "avg": 4.2, "n": 1 }, "Role prompting": { "avg": 3.633, "n": 6 }, "Structured output": { "avg": 4.382, "n": 11 }, "Telco": { "avg": 4.175, "n": 8 }, "Terminal": { "avg": 2.56, "n": 10 } }, "dimensions": { "accuracy": 3.486, "completeness": 3.729, "clarity": 4.234, "domain_expertise": 3.318, "helpfulness": 3.458 }, "tokens_per_second": 126.8 }, { "name": "gemma:latest", "family": "gemma", "params_b": 8.5, "quantization": "Q4_0", "context_length": 8192, "size_bytes": 4781250000, "size_estimated": true, "installed": false, "min_memory_gb": 6.3, "overall": 3.2, "rated": 23, "failed": 8, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "HR": { "avg": 2.6, "n": 2 }, "Health": { "avg": 3.0, "n": 1 }, "LLM": { "avg": 3.1, "n": 2 }, "Linux": { "avg": 2.0, "n": 1 }, "Programming": { "avg": 2.68, "n": 5 }, "RAG": { "avg": 3.4, "n": 1 }, "Reasoning": { "avg": 4.6, "n": 1 }, "Structured output": { "avg": 3.0, "n": 2 }, "Telco": { "avg": 3.75, "n": 4 } }, "dimensions": { "accuracy": 3.217, "completeness": 3.0, "clarity": 4.043, "domain_expertise": 2.783, "helpfulness": 2.957 }, "tokens_per_second": 17.3 }, { "name": "glm-4.7-flash:Q4_K_M", "family": "glm4moelite", "params_b": 29.9, "quantization": "Q4_K_M", "context_length": 202752, "size_bytes": 19019270852, "size_estimated": false, "installed": true, "min_memory_gb": 20.5, "overall": 3.853, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 4.7, "n": 10 }, "Classification - Zero shot": { "avg": 4.7, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Factography": { "avg": 1.6, "n": 1 }, "HR": { "avg": 3.2, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 4.0, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.4, "n": 3 }, "Programming": { "avg": 3.348, "n": 23 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 3.0, "n": 1 }, "Role prompting": { "avg": 3.233, "n": 6 }, "Structured output": { "avg": 4.345, "n": 11 }, "Telco": { "avg": 4.225, "n": 8 } }, "dimensions": { "accuracy": 3.802, "completeness": 3.837, "clarity": 4.442, "domain_expertise": 3.477, "helpfulness": 3.709 }, "tokens_per_second": 87.8 }, { "name": "gpt-oss:20b", "family": "gpt-oss", "params_b": 20.9, "quantization": "MXFP4", "context_length": 131072, "size_bytes": 13793441566, "size_estimated": false, "installed": true, "min_memory_gb": 15.3, "overall": 3.936, "rated": 106, "failed": 2, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.64, "n": 10 }, "Classification - Zero shot": { "avg": 4.7, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 4.0, "n": 2 }, "Factography": { "avg": 1.6, "n": 1 }, "HR": { "avg": 4.0, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 4.0, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 3.533, "n": 3 }, "Programming": { "avg": 3.636, "n": 33 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 4.6, "n": 1 }, "Role prompting": { "avg": 3.233, "n": 6 }, "Structured output": { "avg": 4.327, "n": 11 }, "Telco": { "avg": 4.375, "n": 8 }, "Terminal": { "avg": 3.46, "n": 10 } }, "dimensions": { "accuracy": 3.689, "completeness": 4.179, "clarity": 4.425, "domain_expertise": 3.594, "helpfulness": 3.811 }, "tokens_per_second": 132.8 }, { "name": "granite4.2:3b", "family": "granite", "params_b": 3.7, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 2244023965, "size_estimated": false, "installed": true, "min_memory_gb": 3.7, "overall": 2.765, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 3.06, "n": 10 }, "Classification - Zero shot": { "avg": 2.96, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "Factography": { "avg": 1.9, "n": 2 }, "HR": { "avg": 2.5, "n": 2 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 2.7, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Logic": { "avg": 1.4, "n": 1 }, "Philosophy": { "avg": 3.4, "n": 1 }, "Polski": { "avg": 3.067, "n": 3 }, "Programming": { "avg": 2.352, "n": 33 }, "RAG": { "avg": 3.3, "n": 2 }, "Reasoning": { "avg": 3.8, "n": 1 }, "Role prompting": { "avg": 2.067, "n": 6 }, "Structured output": { "avg": 3.6, "n": 11 }, "Telco": { "avg": 3.35, "n": 8 }, "Terminal": { "avg": 2.24, "n": 10 } }, "dimensions": { "accuracy": 2.917, "completeness": 3.102, "clarity": 2.306, "domain_expertise": 2.907, "helpfulness": 2.593 }, "tokens_per_second": 154.9 }, { "name": "granite4.2:8b", "family": "granite", "params_b": 8.8, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 5347929757, "size_estimated": false, "installed": true, "min_memory_gb": 6.8, "overall": 3.105, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 3.28, "n": 10 }, "Classification - Zero shot": { "avg": 3.32, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "Factography": { "avg": 1.8, "n": 2 }, "HR": { "avg": 2.8, "n": 2 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 2.9, "n": 2 }, "Linux": { "avg": 3.0, "n": 1 }, "Logic": { "avg": 1.4, "n": 1 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Polski": { "avg": 3.267, "n": 3 }, "Programming": { "avg": 2.791, "n": 23 }, "RAG": { "avg": 3.3, "n": 2 }, "Reasoning": { "avg": 3.8, "n": 1 }, "Role prompting": { "avg": 2.667, "n": 6 }, "Structured output": { "avg": 3.564, "n": 11 }, "Telco": { "avg": 3.35, "n": 8 } }, "dimensions": { "accuracy": 3.477, "completeness": 3.432, "clarity": 2.398, "domain_expertise": 3.409, "helpfulness": 2.807 }, "tokens_per_second": 64.7 }, { "name": "granite4:micro", "family": "granite", "params_b": 3.4, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 2082500000, "size_estimated": true, "installed": false, "min_memory_gb": 3.6, "overall": 3.183, "rated": 71, "failed": 17, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 3.98, "n": 10 }, "Classification - Zero shot": { "avg": 3.92, "n": 10 }, "Education": { "avg": 3.4, "n": 1 }, "HR": { "avg": 2.4, "n": 1 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 3.4, "n": 1 }, "Polski": { "avg": 2.0, "n": 1 }, "Programming": { "avg": 2.456, "n": 18 }, "RAG": { "avg": 3.2, "n": 1 }, "Role prompting": { "avg": 1.533, "n": 6 }, "Structured output": { "avg": 3.836, "n": 11 }, "Telco": { "avg": 3.5, "n": 6 } }, "dimensions": { "accuracy": 3.042, "completeness": 3.225, "clarity": 3.944, "domain_expertise": 2.789, "helpfulness": 2.915 }, "tokens_per_second": 189.7 }, { "name": "granite4:tiny-h", "family": "granitehybrid", "params_b": 6.9, "quantization": "Q4_K_M", "context_length": 1048576, "size_bytes": 4226250000, "size_estimated": true, "installed": false, "min_memory_gb": 5.7, "overall": 3.122, "rated": 74, "failed": 14, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 3.44, "n": 10 }, "Classification - Zero shot": { "avg": 3.42, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 3.7, "n": 2 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 1.6, "n": 2 }, "Programming": { "avg": 2.655, "n": 22 }, "RAG": { "avg": 3.0, "n": 2 }, "Role prompting": { "avg": 2.267, "n": 6 }, "Structured output": { "avg": 3.62, "n": 10 }, "Telco": { "avg": 3.95, "n": 4 } }, "dimensions": { "accuracy": 2.905, "completeness": 3.108, "clarity": 4.135, "domain_expertise": 2.743, "helpfulness": 2.73 }, "tokens_per_second": 73.0 }, { "name": "hf.co/lmstudio-community/Qwen3-4B-Instruct-2507-GGUF:Q6_K", "family": "qwen3", "params_b": 4.02, "quantization": "Q6_K", "context_length": 262144, "size_bytes": 3306263061, "size_estimated": false, "installed": true, "min_memory_gb": 4.8, "overall": 3.488, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.16, "n": 10 }, "Classification - Zero shot": { "avg": 4.26, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 1.6, "n": 1 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Linux": { "avg": 2.6, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.133, "n": 3 }, "Programming": { "avg": 2.765, "n": 23 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 2.667, "n": 6 }, "Structured output": { "avg": 4.127, "n": 11 }, "Telco": { "avg": 3.875, "n": 8 } }, "dimensions": { "accuracy": 3.279, "completeness": 3.57, "clarity": 4.233, "domain_expertise": 3.128, "helpfulness": 3.244 }, "tokens_per_second": 75.6 }, { "name": "hf.co/lmstudio-community/Qwen3-4B-Thinking-2507-GGUF:Q6_K", "family": "qwen3", "params_b": 4.02, "quantization": "Q6_K", "context_length": 262144, "size_bytes": 3306263061, "size_estimated": false, "installed": true, "min_memory_gb": 4.8, "overall": 3.184, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 3.46, "n": 10 }, "Classification - Zero shot": { "avg": 3.6, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.4, "n": 2 }, "Factography": { "avg": 1.3, "n": 2 }, "HR": { "avg": 3.3, "n": 2 }, "Health": { "avg": 3.0, "n": 1 }, "LLM": { "avg": 3.0, "n": 2 }, "Linux": { "avg": 3.6, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 1.333, "n": 3 }, "Programming": { "avg": 2.591, "n": 23 }, "RAG": { "avg": 3.5, "n": 2 }, "Reasoning": { "avg": 4.4, "n": 1 }, "Role prompting": { "avg": 3.367, "n": 6 }, "Structured output": { "avg": 3.509, "n": 11 }, "Telco": { "avg": 4.025, "n": 8 } }, "dimensions": { "accuracy": 3.276, "completeness": 3.414, "clarity": 2.954, "domain_expertise": 3.287, "helpfulness": 2.989 }, "tokens_per_second": 68.0 }, { "name": "hf.co/speakleash/Bielik-1.5B-v3.0-Instruct-GGUF:Q8_0", "family": "llama", "params_b": 1.6, "quantization": "unknown", "context_length": 8192, "size_bytes": 980000000, "size_estimated": true, "installed": false, "min_memory_gb": 2.5, "overall": 2.281, "rated": 37, "failed": 7, "categories": { "AI": { "avg": 3.0, "n": 1 }, "Creative": { "avg": 2.8, "n": 1 }, "Education": { "avg": 1.9, "n": 2 }, "HR": { "avg": 2.1, "n": 2 }, "Health": { "avg": 2.2, "n": 1 }, "LLM": { "avg": 2.3, "n": 2 }, "Linux": { "avg": 1.0, "n": 1 }, "Philosophy": { "avg": 3.4, "n": 1 }, "Polski": { "avg": 1.8, "n": 2 }, "Programming": { "avg": 1.875, "n": 8 }, "RAG": { "avg": 1.8, "n": 2 }, "Reasoning": { "avg": 1.2, "n": 1 }, "Structured output": { "avg": 2.48, "n": 10 }, "Telco": { "avg": 3.733, "n": 3 } }, "dimensions": { "accuracy": 2.189, "completeness": 2.162, "clarity": 3.081, "domain_expertise": 2.081, "helpfulness": 1.919 }, "tokens_per_second": 79.0 }, { "name": "hf.co/speakleash/Bielik-11B-v2.6-Instruct-GGUF:Q4_K_M", "family": "llama", "params_b": 11.2, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 6724052244, "size_estimated": false, "installed": true, "min_memory_gb": 8.2, "overall": 3.311, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 4.14, "n": 10 }, "Classification - Zero shot": { "avg": 3.96, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "Factography": { "avg": 2.4, "n": 1 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 3.2, "n": 2 }, "Linux": { "avg": 3.2, "n": 1 }, "Philosophy": { "avg": 3.4, "n": 1 }, "Polski": { "avg": 3.467, "n": 3 }, "Programming": { "avg": 2.548, "n": 23 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 2.6, "n": 1 }, "Role prompting": { "avg": 3.4, "n": 6 }, "Structured output": { "avg": 4.08, "n": 10 }, "Telco": { "avg": 2.7, "n": 8 } }, "dimensions": { "accuracy": 3.259, "completeness": 3.2, "clarity": 4.094, "domain_expertise": 2.976, "helpfulness": 3.012 }, "tokens_per_second": 19.0 }, { "name": "hf.co/speakleash/Bielik-11B-v2.6-Instruct-GGUF:Q5_K_M", "family": "llama", "params_b": 11.2, "quantization": "unknown", "context_length": 32768, "size_bytes": 6860000000, "size_estimated": true, "installed": false, "min_memory_gb": 8.4, "overall": 3.372, "rated": 29, "failed": 2, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.7, "n": 2 }, "Linux": { "avg": 2.8, "n": 1 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Programming": { "avg": 3.057, "n": 7 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 1.8, "n": 1 }, "Structured output": { "avg": 2.9, "n": 2 }, "Telco": { "avg": 3.9, "n": 6 } }, "dimensions": { "accuracy": 3.276, "completeness": 3.414, "clarity": 4.103, "domain_expertise": 3.0, "helpfulness": 3.069 }, "tokens_per_second": 8.4 }, { "name": "hf.co/speakleash/Bielik-11B-v3.0-Instruct-GGUF:Q6_K", "family": "llama", "params_b": 11.2, "quantization": "unknown", "context_length": 32768, "size_bytes": 6860000000, "size_estimated": true, "installed": false, "min_memory_gb": 8.4, "overall": 3.291, "rated": 77, "failed": 3, "categories": { "AI": { "avg": 2.8, "n": 1 }, "Classification - Few shot": { "avg": 4.34, "n": 10 }, "Classification - Zero shot": { "avg": 4.02, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 2.9, "n": 2 }, "Factography": { "avg": 1.6, "n": 1 }, "HR": { "avg": 3.5, "n": 2 }, "Health": { "avg": 3.0, "n": 1 }, "LLM": { "avg": 3.6, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 2.133, "n": 3 }, "Programming": { "avg": 2.555, "n": 22 }, "RAG": { "avg": 3.4, "n": 2 }, "Reasoning": { "avg": 2.2, "n": 1 }, "Structured output": { "avg": 3.818, "n": 11 }, "Telco": { "avg": 3.167, "n": 6 } }, "dimensions": { "accuracy": 3.234, "completeness": 3.26, "clarity": 4.156, "domain_expertise": 2.87, "helpfulness": 2.935 }, "tokens_per_second": 74.8 }, { "name": "hf.co/speakleash/Bielik-4.5B-v3.0-Instruct-GGUF:Q8_0", "family": "llama", "params_b": 4.76, "quantization": "unknown", "context_length": 8192, "size_bytes": 2915500000, "size_estimated": true, "installed": false, "min_memory_gb": 4.4, "overall": 2.93, "rated": 40, "failed": 4, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 3.2, "n": 1 }, "Polski": { "avg": 2.2, "n": 2 }, "Programming": { "avg": 2.525, "n": 8 }, "RAG": { "avg": 2.3, "n": 2 }, "Reasoning": { "avg": 1.6, "n": 1 }, "Structured output": { "avg": 3.08, "n": 10 }, "Telco": { "avg": 3.2, "n": 6 } }, "dimensions": { "accuracy": 2.75, "completeness": 2.925, "clarity": 3.675, "domain_expertise": 2.6, "helpfulness": 2.7 }, "tokens_per_second": 36.7 }, { "name": "hf.co/unsloth/medgemma-1.5-4b-it-GGUF:Q8_K_XL", "family": "gemma3", "params_b": 3.88, "quantization": "Q8_0", "context_length": 131072, "size_bytes": 6016459591, "size_estimated": false, "installed": true, "min_memory_gb": 7.5, "overall": 2.909, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 3.4, "n": 10 }, "Classification - Zero shot": { "avg": 2.86, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Factography": { "avg": 1.2, "n": 1 }, "HR": { "avg": 3.6, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 2.9, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Philosophy": { "avg": 3.6, "n": 1 }, "Polski": { "avg": 1.867, "n": 3 }, "Programming": { "avg": 2.061, "n": 23 }, "RAG": { "avg": 3.4, "n": 2 }, "Reasoning": { "avg": 4.2, "n": 1 }, "Role prompting": { "avg": 3.033, "n": 6 }, "Structured output": { "avg": 3.345, "n": 11 }, "Telco": { "avg": 3.65, "n": 8 } }, "dimensions": { "accuracy": 2.826, "completeness": 3.105, "clarity": 3.128, "domain_expertise": 2.826, "helpfulness": 2.64 }, "tokens_per_second": 110.5 }, { "name": "huggingface.co/NikolayKozloff/PLLuM-12B-instruct-Q5_K_M-GGUF:latest", "family": "llama", "params_b": 12.2, "quantization": "unknown", "context_length": 131072, "size_bytes": 7472500000, "size_estimated": true, "installed": false, "min_memory_gb": 9.0, "overall": 2.552, "rated": 33, "failed": 11, "categories": { "AI": { "avg": 3.0, "n": 1 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 2.5, "n": 2 }, "Health": { "avg": 2.0, "n": 1 }, "LLM": { "avg": 2.8, "n": 2 }, "Polski": { "avg": 1.133, "n": 3 }, "Programming": { "avg": 1.88, "n": 5 }, "Reasoning": { "avg": 3.4, "n": 1 }, "Structured output": { "avg": 2.582, "n": 11 }, "Telco": { "avg": 3.4, "n": 6 } }, "dimensions": { "accuracy": 2.879, "completeness": 2.424, "clarity": 2.879, "domain_expertise": 2.394, "helpfulness": 2.182 }, "tokens_per_second": 7.4 }, { "name": "huggingface.co/Triangle104/OpenReasoning-Nemotron-7B-Q5_K_M-GGUF:latest", "family": "qwen2", "params_b": 7.62, "quantization": "unknown", "context_length": 131072, "size_bytes": 4667250000, "size_estimated": true, "installed": false, "min_memory_gb": 6.2, "overall": 2.335, "rated": 43, "failed": 1, "categories": { "AI": { "avg": 3.2, "n": 1 }, "Creative": { "avg": 3.2, "n": 1 }, "Education": { "avg": 2.9, "n": 2 }, "HR": { "avg": 1.6, "n": 2 }, "Health": { "avg": 1.8, "n": 1 }, "LLM": { "avg": 2.2, "n": 2 }, "Linux": { "avg": 1.0, "n": 1 }, "Philosophy": { "avg": 1.6, "n": 1 }, "Polski": { "avg": 1.4, "n": 2 }, "Programming": { "avg": 2.25, "n": 8 }, "RAG": { "avg": 1.8, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Structured output": { "avg": 2.455, "n": 11 }, "Telco": { "avg": 2.6, "n": 8 } }, "dimensions": { "accuracy": 2.279, "completeness": 2.581, "clarity": 2.163, "domain_expertise": 2.395, "helpfulness": 2.233 }, "tokens_per_second": 44.4 }, { "name": "huggingface.co/pswitala/pllum-8b-instruct-q5_k_m_gguf:latest", "family": "llama", "params_b": 8.03, "quantization": "unknown", "context_length": 131072, "size_bytes": 4918375000, "size_estimated": true, "installed": false, "min_memory_gb": 6.4, "overall": 2.876, "rated": 37, "failed": 7, "categories": { "AI": { "avg": 2.8, "n": 1 }, "Creative": { "avg": 2.8, "n": 1 }, "Education": { "avg": 2.8, "n": 2 }, "HR": { "avg": 3.0, "n": 1 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.3, "n": 2 }, "Philosophy": { "avg": 2.6, "n": 1 }, "Polski": { "avg": 1.0, "n": 3 }, "Programming": { "avg": 2.5, "n": 8 }, "RAG": { "avg": 2.4, "n": 1 }, "Structured output": { "avg": 3.18, "n": 10 }, "Telco": { "avg": 3.733, "n": 6 } }, "dimensions": { "accuracy": 2.946, "completeness": 2.568, "clarity": 3.649, "domain_expertise": 2.622, "helpfulness": 2.595 }, "tokens_per_second": 29.0 }, { "name": "huggingface.co/speakleash/Bielik-11B-v2.3-Instruct-GGUF:latest", "family": "llama", "params_b": 11.2, "quantization": "unknown", "context_length": 32768, "size_bytes": 6860000000, "size_estimated": true, "installed": false, "min_memory_gb": 8.4, "overall": 3.255, "rated": 40, "failed": 4, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 2.9, "n": 2 }, "HR": { "avg": 3.1, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Linux": { "avg": 3.2, "n": 1 }, "Philosophy": { "avg": 3.2, "n": 1 }, "Polski": { "avg": 1.533, "n": 3 }, "Programming": { "avg": 2.9, "n": 8 }, "RAG": { "avg": 3.4, "n": 1 }, "Structured output": { "avg": 3.636, "n": 11 }, "Telco": { "avg": 3.733, "n": 6 } }, "dimensions": { "accuracy": 3.3, "completeness": 3.175, "clarity": 4.05, "domain_expertise": 2.9, "helpfulness": 2.9 }, "tokens_per_second": 4.6 }, { "name": "huggingface.co/unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF:Q4_K_M", "family": "llama", "params_b": 23.6, "quantization": "unknown", "context_length": 131072, "size_bytes": 14455000000, "size_estimated": true, "installed": false, "min_memory_gb": 16.0, "overall": 3.41, "rated": 39, "failed": 5, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "HR": { "avg": 3.2, "n": 2 }, "Health": { "avg": 2.2, "n": 1 }, "LLM": { "avg": 2.8, "n": 2 }, "Linux": { "avg": 2.8, "n": 1 }, "Philosophy": { "avg": 3.2, "n": 1 }, "Polski": { "avg": 1.8, "n": 3 }, "Programming": { "avg": 3.033, "n": 6 }, "RAG": { "avg": 2.8, "n": 1 }, "Structured output": { "avg": 3.873, "n": 11 }, "Telco": { "avg": 4.171, "n": 7 } }, "dimensions": { "accuracy": 3.513, "completeness": 3.333, "clarity": 3.718, "domain_expertise": 3.256, "helpfulness": 3.231 }, "tokens_per_second": 3.3 }, { "name": "laguna-xs-2.1:latest", "family": "laguna", "params_b": 33.4, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 20274303147, "size_estimated": false, "installed": true, "min_memory_gb": 21.8, "overall": 3.781, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 4.44, "n": 10 }, "Classification - Zero shot": { "avg": 4.46, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "Factography": { "avg": 1.6, "n": 2 }, "HR": { "avg": 3.6, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 4.0, "n": 2 }, "Linux": { "avg": 3.6, "n": 1 }, "Logic": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 3.2, "n": 3 }, "Programming": { "avg": 3.479, "n": 33 }, "RAG": { "avg": 4.0, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 2.867, "n": 6 }, "Structured output": { "avg": 4.309, "n": 11 }, "Telco": { "avg": 4.25, "n": 8 }, "Terminal": { "avg": 3.62, "n": 10 } }, "dimensions": { "accuracy": 3.667, "completeness": 3.917, "clarity": 4.269, "domain_expertise": 3.435, "helpfulness": 3.62 }, "tokens_per_second": 125.9 }, { "name": "lfm2.5-thinking:1.2b", "family": "lfm2", "params_b": 1.2, "quantization": "Q4_K_M", "context_length": 128000, "size_bytes": 731163903, "size_estimated": false, "installed": true, "min_memory_gb": 2.2, "overall": 2.007, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 1.24, "n": 10 }, "Classification - Zero shot": { "avg": 1.5, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.2, "n": 2 }, "Factography": { "avg": 1.0, "n": 1 }, "HR": { "avg": 1.1, "n": 2 }, "Health": { "avg": 3.8, "n": 1 }, "LLM": { "avg": 3.0, "n": 2 }, "Linux": { "avg": 1.0, "n": 1 }, "Philosophy": { "avg": 2.6, "n": 1 }, "Polski": { "avg": 1.067, "n": 3 }, "Programming": { "avg": 2.026, "n": 23 }, "RAG": { "avg": 1.7, "n": 2 }, "Reasoning": { "avg": 3.8, "n": 1 }, "Role prompting": { "avg": 1.767, "n": 6 }, "Structured output": { "avg": 2.527, "n": 11 }, "Telco": { "avg": 2.4, "n": 8 } }, "dimensions": { "accuracy": 1.965, "completeness": 2.116, "clarity": 2.198, "domain_expertise": 1.884, "helpfulness": 1.86 }, "tokens_per_second": 508.3 }, { "name": "lfm2:24b", "family": "lfm2moe", "params_b": 23.8, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 14415742358, "size_estimated": false, "installed": true, "min_memory_gb": 15.9, "overall": 3.122, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 4.4, "n": 1 }, "Classification - Few shot": { "avg": 3.48, "n": 10 }, "Classification - Zero shot": { "avg": 2.62, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 1.2, "n": 1 }, "HR": { "avg": 3.2, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 4.2, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Logic": { "avg": 1.8, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.0, "n": 3 }, "Programming": { "avg": 2.974, "n": 23 }, "RAG": { "avg": 3.5, "n": 2 }, "Reasoning": { "avg": 1.4, "n": 1 }, "Role prompting": { "avg": 3.233, "n": 6 }, "Structured output": { "avg": 3.564, "n": 11 }, "Telco": { "avg": 3.15, "n": 8 } }, "dimensions": { "accuracy": 2.839, "completeness": 3.092, "clarity": 4.138, "domain_expertise": 2.759, "helpfulness": 2.782 }, "tokens_per_second": 75.0 }, { "name": "lfm3-audio:latest", "family": "lfm3", "params_b": 1.7, "quantization": "Q4_K_M", "context_length": 128000, "size_bytes": 1670483243, "size_estimated": false, "installed": true, "min_memory_gb": 3.2, "overall": 2.675, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 2.44, "n": 10 }, "Classification - Zero shot": { "avg": 3.42, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "Factography": { "avg": 1.2, "n": 2 }, "HR": { "avg": 2.7, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 2.9, "n": 2 }, "Linux": { "avg": 1.4, "n": 1 }, "Logic": { "avg": 1.8, "n": 1 }, "Philosophy": { "avg": 2.4, "n": 1 }, "Polski": { "avg": 3.0, "n": 3 }, "Programming": { "avg": 1.93, "n": 23 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 1.8, "n": 1 }, "Role prompting": { "avg": 2.933, "n": 6 }, "Structured output": { "avg": 3.455, "n": 11 }, "Telco": { "avg": 2.625, "n": 8 } }, "dimensions": { "accuracy": 2.636, "completeness": 2.58, "clarity": 3.443, "domain_expertise": 2.409, "helpfulness": 2.307 }, "tokens_per_second": 283.3 }, { "name": "lfm3-omni:latest", "family": "lfm3", "params_b": 1.7, "quantization": "Q4_K_M", "context_length": 128000, "size_bytes": 2049482162, "size_estimated": false, "installed": true, "min_memory_gb": 3.5, "overall": 2.509, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 3.4, "n": 10 }, "Classification - Zero shot": { "avg": 3.76, "n": 10 }, "Creative": { "avg": 1.8, "n": 1 }, "Education": { "avg": 2.7, "n": 2 }, "Factography": { "avg": 1.3, "n": 2 }, "HR": { "avg": 1.9, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 1.6, "n": 1 }, "Logic": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 3.0, "n": 1 }, "Polski": { "avg": 3.133, "n": 3 }, "Programming": { "avg": 1.897, "n": 33 }, "RAG": { "avg": 2.5, "n": 2 }, "Reasoning": { "avg": 1.6, "n": 1 }, "Role prompting": { "avg": 2.6, "n": 6 }, "Structured output": { "avg": 3.618, "n": 11 }, "Telco": { "avg": 2.425, "n": 8 }, "Terminal": { "avg": 1.14, "n": 10 } }, "dimensions": { "accuracy": 2.25, "completeness": 2.602, "clarity": 3.343, "domain_expertise": 2.12, "helpfulness": 2.222 }, "tokens_per_second": 322.7 }, { "name": "lfm3-vl:latest", "family": "lfm3", "params_b": 1.7, "quantization": "Q4_K_M", "context_length": 128000, "size_bytes": 1478634721, "size_estimated": false, "installed": true, "min_memory_gb": 3.0, "overall": 3.13, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.2, "n": 10 }, "Classification - Zero shot": { "avg": 4.46, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.4, "n": 2 }, "Factography": { "avg": 1.4, "n": 2 }, "HR": { "avg": 2.4, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 3.4, "n": 2 }, "Linux": { "avg": 1.4, "n": 1 }, "Logic": { "avg": 3.2, "n": 1 }, "Philosophy": { "avg": 3.4, "n": 1 }, "Polski": { "avg": 2.6, "n": 3 }, "Programming": { "avg": 2.122, "n": 23 }, "RAG": { "avg": 3.0, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 2.2, "n": 6 }, "Structured output": { "avg": 3.927, "n": 11 }, "Telco": { "avg": 3.05, "n": 8 } }, "dimensions": { "accuracy": 2.898, "completeness": 3.284, "clarity": 3.864, "domain_expertise": 2.682, "helpfulness": 2.92 }, "tokens_per_second": 259.2 }, { "name": "llama3.1:8b", "family": "llama", "params_b": 8.0, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 4920753328, "size_estimated": false, "installed": true, "min_memory_gb": 6.4, "overall": 3.202, "rated": 81, "failed": 7, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 3.96, "n": 10 }, "Classification - Zero shot": { "avg": 4.02, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.2, "n": 2 }, "Factography": { "avg": 2.4, "n": 1 }, "HR": { "avg": 1.6, "n": 1 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 2.6, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 2.067, "n": 3 }, "Programming": { "avg": 2.427, "n": 22 }, "RAG": { "avg": 2.9, "n": 2 }, "Role prompting": { "avg": 2.033, "n": 6 }, "Structured output": { "avg": 3.818, "n": 11 }, "Telco": { "avg": 4.267, "n": 6 } }, "dimensions": { "accuracy": 3.123, "completeness": 3.148, "clarity": 3.938, "domain_expertise": 2.827, "helpfulness": 2.975 }, "tokens_per_second": 130.7 }, { "name": "llama3.2:latest", "family": "llama", "params_b": 3.2, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 2019393189, "size_estimated": false, "installed": true, "min_memory_gb": 3.5, "overall": 2.411, "rated": 94, "failed": 14, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 2.88, "n": 10 }, "Classification - Zero shot": { "avg": 2.96, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "HR": { "avg": 1.8, "n": 1 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 3.4, "n": 2 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Polski": { "avg": 1.467, "n": 3 }, "Programming": { "avg": 2.006, "n": 32 }, "RAG": { "avg": 2.2, "n": 1 }, "Role prompting": { "avg": 1.6, "n": 6 }, "Structured output": { "avg": 3.44, "n": 10 }, "Telco": { "avg": 3.533, "n": 3 }, "Terminal": { "avg": 1.34, "n": 10 } }, "dimensions": { "accuracy": 2.255, "completeness": 2.426, "clarity": 3.181, "domain_expertise": 2.085, "helpfulness": 2.106 }, "tokens_per_second": 234.1 }, { "name": "llama3.3:latest", "family": "llama", "params_b": 70.6, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 43242500000, "size_estimated": true, "installed": false, "min_memory_gb": 44.7, "overall": 3.795, "rated": 81, "failed": 1, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.44, "n": 10 }, "Classification - Zero shot": { "avg": 4.68, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Factography": { "avg": 1.6, "n": 1 }, "HR": { "avg": 3.6, "n": 2 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 4.0, "n": 2 }, "Linux": { "avg": 3.4, "n": 1 }, "Logic": { "avg": 4.4, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.4, "n": 3 }, "Programming": { "avg": 2.913, "n": 23 }, "RAG": { "avg": 3.3, "n": 2 }, "Reasoning": { "avg": 4.6, "n": 1 }, "Structured output": { "avg": 4.4, "n": 11 }, "Telco": { "avg": 4.4, "n": 8 } }, "dimensions": { "accuracy": 3.815, "completeness": 3.728, "clarity": 4.506, "domain_expertise": 3.37, "helpfulness": 3.556 }, "tokens_per_second": 1.1 }, { "name": "llava:latest", "family": "clip", "params_b": 0.31, "quantization": "Q4_0", "context_length": 32768, "size_bytes": 175438125, "size_estimated": true, "installed": false, "min_memory_gb": 1.7, "overall": 2.618, "rated": 79, "failed": 9, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 2.74, "n": 10 }, "Classification - Zero shot": { "avg": 2.82, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.0, "n": 2 }, "HR": { "avg": 2.2, "n": 1 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 3.6, "n": 2 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 1.133, "n": 3 }, "Programming": { "avg": 2.1, "n": 22 }, "RAG": { "avg": 2.8, "n": 2 }, "Role prompting": { "avg": 1.6, "n": 6 }, "Structured output": { "avg": 3.255, "n": 11 }, "Telco": { "avg": 3.567, "n": 6 } }, "dimensions": { "accuracy": 2.456, "completeness": 2.557, "clarity": 3.671, "domain_expertise": 2.241, "helpfulness": 2.165 }, "tokens_per_second": 157.7 }, { "name": "ministral-3:14b", "family": "mistral3", "params_b": 13.9, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 9082525626, "size_estimated": false, "installed": true, "min_memory_gb": 10.6, "overall": 3.738, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.02, "n": 10 }, "Classification - Zero shot": { "avg": 4.22, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.4, "n": 2 }, "Factography": { "avg": 1.7, "n": 2 }, "HR": { "avg": 3.6, "n": 2 }, "Health": { "avg": 4.6, "n": 1 }, "LLM": { "avg": 4.0, "n": 2 }, "Linux": { "avg": 3.6, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 2.6, "n": 3 }, "Programming": { "avg": 3.226, "n": 23 }, "RAG": { "avg": 4.0, "n": 2 }, "Reasoning": { "avg": 4.6, "n": 1 }, "Role prompting": { "avg": 3.433, "n": 6 }, "Structured output": { "avg": 4.182, "n": 11 }, "Telco": { "avg": 4.425, "n": 8 } }, "dimensions": { "accuracy": 3.483, "completeness": 3.897, "clarity": 4.448, "domain_expertise": 3.345, "helpfulness": 3.517 }, "tokens_per_second": 76.1 }, { "name": "ministral-3:3b", "family": "mistral3", "params_b": 3.8, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 2953828889, "size_estimated": false, "installed": true, "min_memory_gb": 4.5, "overall": 3.107, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 3.16, "n": 10 }, "Classification - Zero shot": { "avg": 3.08, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.4, "n": 2 }, "Factography": { "avg": 1.8, "n": 1 }, "HR": { "avg": 3.3, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 2.0, "n": 3 }, "Programming": { "avg": 2.748, "n": 23 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 2.0, "n": 1 }, "Role prompting": { "avg": 3.067, "n": 6 }, "Structured output": { "avg": 3.727, "n": 11 }, "Telco": { "avg": 3.25, "n": 8 } }, "dimensions": { "accuracy": 2.651, "completeness": 3.174, "clarity": 4.209, "domain_expertise": 2.733, "helpfulness": 2.767 }, "tokens_per_second": 191.6 }, { "name": "ministral-3:8b", "family": "mistral3", "params_b": 8.9, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 6022224665, "size_estimated": false, "installed": true, "min_memory_gb": 7.5, "overall": 3.541, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.02, "n": 10 }, "Classification - Zero shot": { "avg": 3.96, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 2.0, "n": 2 }, "HR": { "avg": 3.7, "n": 2 }, "Health": { "avg": 4.2, "n": 1 }, "LLM": { "avg": 3.9, "n": 2 }, "Linux": { "avg": 3.2, "n": 1 }, "Logic": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 2.467, "n": 3 }, "Programming": { "avg": 3.104, "n": 23 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 1.6, "n": 1 }, "Role prompting": { "avg": 3.5, "n": 6 }, "Structured output": { "avg": 3.909, "n": 11 }, "Telco": { "avg": 3.95, "n": 8 } }, "dimensions": { "accuracy": 3.318, "completeness": 3.557, "clarity": 4.284, "domain_expertise": 3.261, "helpfulness": 3.284 }, "tokens_per_second": 113.4 }, { "name": "mistral-nemo:latest", "family": "llama", "params_b": 12.2, "quantization": "Q4_0", "context_length": 1024000, "size_bytes": 6862500000, "size_estimated": true, "installed": false, "min_memory_gb": 8.4, "overall": 3.299, "rated": 77, "failed": 3, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 4.12, "n": 10 }, "Classification - Zero shot": { "avg": 3.02, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "Factography": { "avg": 1.4, "n": 1 }, "HR": { "avg": 3.0, "n": 2 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 3.6, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 1.8, "n": 3 }, "Programming": { "avg": 2.591, "n": 23 }, "RAG": { "avg": 3.3, "n": 2 }, "Structured output": { "avg": 4.073, "n": 11 }, "Telco": { "avg": 4.467, "n": 6 } }, "dimensions": { "accuracy": 3.104, "completeness": 3.325, "clarity": 4.195, "domain_expertise": 2.922, "helpfulness": 2.948 }, "tokens_per_second": 16.9 }, { "name": "mistral-small3.2:24b", "family": "mistral3", "params_b": 24.0, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 15177384862, "size_estimated": false, "installed": true, "min_memory_gb": 16.7, "overall": 3.716, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 4.5, "n": 10 }, "Classification - Zero shot": { "avg": 3.96, "n": 10 }, "Creative": { "avg": 4.4, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "Factography": { "avg": 2.0, "n": 1 }, "HR": { "avg": 3.5, "n": 2 }, "Health": { "avg": 3.8, "n": 1 }, "LLM": { "avg": 3.9, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.4, "n": 3 }, "Programming": { "avg": 3.2, "n": 23 }, "RAG": { "avg": 3.5, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 3.4, "n": 6 }, "Structured output": { "avg": 4.182, "n": 11 }, "Telco": { "avg": 4.375, "n": 8 } }, "dimensions": { "accuracy": 3.64, "completeness": 3.663, "clarity": 4.488, "domain_expertise": 3.314, "helpfulness": 3.488 }, "tokens_per_second": 30.2 }, { "name": "mistral:7b", "family": "llama", "params_b": 7.2, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 4372824384, "size_estimated": false, "installed": true, "min_memory_gb": 5.9, "overall": 3.026, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 4.22, "n": 10 }, "Classification - Zero shot": { "avg": 3.46, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "HR": { "avg": 2.7, "n": 2 }, "Health": { "avg": 3.8, "n": 1 }, "LLM": { "avg": 3.3, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 1.667, "n": 3 }, "Programming": { "avg": 2.391, "n": 23 }, "RAG": { "avg": 3.3, "n": 2 }, "Reasoning": { "avg": 1.2, "n": 1 }, "Role prompting": { "avg": 2.167, "n": 6 }, "Structured output": { "avg": 3.545, "n": 11 }, "Telco": { "avg": 3.1, "n": 8 } }, "dimensions": { "accuracy": 2.953, "completeness": 2.929, "clarity": 3.847, "domain_expertise": 2.776, "helpfulness": 2.624 }, "tokens_per_second": 151.9 }, { "name": "mistral:latest", "family": "llama", "params_b": 7.2, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 4372824384, "size_estimated": false, "installed": true, "min_memory_gb": 5.9, "overall": 3.095, "rated": 78, "failed": 10, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 4.36, "n": 10 }, "Classification - Zero shot": { "avg": 3.56, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "HR": { "avg": 3.0, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 2.7, "n": 2 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 1.733, "n": 3 }, "Programming": { "avg": 2.41, "n": 21 }, "RAG": { "avg": 2.6, "n": 1 }, "Role prompting": { "avg": 2.067, "n": 6 }, "Structured output": { "avg": 3.164, "n": 11 }, "Telco": { "avg": 3.933, "n": 6 } }, "dimensions": { "accuracy": 3.0, "completeness": 3.038, "clarity": 3.885, "domain_expertise": 2.795, "helpfulness": 2.756 }, "tokens_per_second": 142.8 }, { "name": "mistral_telco:latest", "family": "llama", "params_b": 7.2, "quantization": "Q5_K_M", "context_length": 32768, "size_bytes": 5136179807, "size_estimated": false, "installed": true, "min_memory_gb": 6.6, "overall": 2.861, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 3.0, "n": 1 }, "Classification - Few shot": { "avg": 3.92, "n": 10 }, "Classification - Zero shot": { "avg": 3.28, "n": 10 }, "Creative": { "avg": 2.4, "n": 1 }, "Education": { "avg": 1.9, "n": 2 }, "HR": { "avg": 2.5, "n": 2 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 3.0, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 1.6, "n": 1 }, "Polski": { "avg": 2.267, "n": 3 }, "Programming": { "avg": 2.226, "n": 23 }, "RAG": { "avg": 2.4, "n": 2 }, "Reasoning": { "avg": 1.4, "n": 1 }, "Role prompting": { "avg": 2.567, "n": 6 }, "Structured output": { "avg": 3.255, "n": 11 }, "Telco": { "avg": 3.625, "n": 8 } }, "dimensions": { "accuracy": 3.012, "completeness": 2.506, "clarity": 3.824, "domain_expertise": 2.612, "helpfulness": 2.341 }, "tokens_per_second": 139.1 }, { "name": "muse-glimmer:30b-q4_K_M-dflash", "family": "muse-glimmer", "params_b": 27.9, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 19788215642, "size_estimated": false, "installed": true, "min_memory_gb": 21.3, "overall": 4.211, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.54, "n": 10 }, "Classification - Zero shot": { "avg": 4.7, "n": 10 }, "Creative": { "avg": 4.6, "n": 1 }, "Education": { "avg": 3.9, "n": 2 }, "Factography": { "avg": 2.0, "n": 2 }, "HR": { "avg": 3.6, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 4.3, "n": 2 }, "Linux": { "avg": 4.0, "n": 1 }, "Logic": { "avg": 4.2, "n": 1 }, "Philosophy": { "avg": 4.6, "n": 1 }, "Polski": { "avg": 4.4, "n": 3 }, "Programming": { "avg": 3.976, "n": 33 }, "RAG": { "avg": 4.2, "n": 2 }, "Reasoning": { "avg": 4.4, "n": 1 }, "Role prompting": { "avg": 4.267, "n": 6 }, "Structured output": { "avg": 4.491, "n": 11 }, "Telco": { "avg": 4.25, "n": 8 }, "Terminal": { "avg": 4.34, "n": 10 } }, "dimensions": { "accuracy": 4.194, "completeness": 4.269, "clarity": 4.565, "domain_expertise": 3.981, "helpfulness": 4.046 }, "tokens_per_second": 31.1 }, { "name": "nemotron-3-nano:30b", "family": "nemotron_h_moe", "params_b": 31.6, "quantization": "Q4_K_M", "context_length": 1048576, "size_bytes": 19355000000, "size_estimated": true, "installed": false, "min_memory_gb": 20.9, "overall": 3.078, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 3.18, "n": 10 }, "Classification - Zero shot": { "avg": 3.46, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Factography": { "avg": 1.3, "n": 2 }, "HR": { "avg": 2.8, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 2.7, "n": 2 }, "Linux": { "avg": 2.8, "n": 1 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Polski": { "avg": 1.733, "n": 3 }, "Programming": { "avg": 2.67, "n": 23 }, "RAG": { "avg": 3.1, "n": 2 }, "Reasoning": { "avg": 3.6, "n": 1 }, "Role prompting": { "avg": 2.9, "n": 6 }, "Structured output": { "avg": 3.673, "n": 11 }, "Telco": { "avg": 3.55, "n": 8 } }, "dimensions": { "accuracy": 3.276, "completeness": 3.46, "clarity": 2.494, "domain_expertise": 3.287, "helpfulness": 2.885 }, "tokens_per_second": 28.4 }, { "name": "nemotron-3.5-lightning:latest", "family": "nemotron_h_moe", "params_b": 32.9, "quantization": "Q4_K_M", "context_length": 1048576, "size_bytes": 25430749387, "size_estimated": false, "installed": true, "min_memory_gb": 26.9, "overall": 3.881, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.72, "n": 10 }, "Classification - Zero shot": { "avg": 4.74, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "Factography": { "avg": 2.4, "n": 2 }, "HR": { "avg": 3.6, "n": 2 }, "Health": { "avg": 4.2, "n": 1 }, "LLM": { "avg": 4.2, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Logic": { "avg": 2.0, "n": 1 }, "Philosophy": { "avg": 4.6, "n": 1 }, "Polski": { "avg": 3.6, "n": 3 }, "Programming": { "avg": 3.473, "n": 33 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 3.6, "n": 6 }, "Structured output": { "avg": 4.236, "n": 11 }, "Telco": { "avg": 4.375, "n": 8 }, "Terminal": { "avg": 3.34, "n": 10 } }, "dimensions": { "accuracy": 3.713, "completeness": 3.972, "clarity": 4.389, "domain_expertise": 3.657, "helpfulness": 3.685 }, "tokens_per_second": 108.4 }, { "name": "nemotron-cascade-2:latest", "family": "nemotron_h_moe", "params_b": 31.6, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 19355000000, "size_estimated": true, "installed": false, "min_memory_gb": 20.9, "overall": 3.143, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 3.42, "n": 10 }, "Classification - Zero shot": { "avg": 3.52, "n": 10 }, "Creative": { "avg": 3.2, "n": 1 }, "Education": { "avg": 2.8, "n": 2 }, "Factography": { "avg": 1.4, "n": 2 }, "HR": { "avg": 3.1, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 3.1, "n": 2 }, "Linux": { "avg": 3.4, "n": 1 }, "Logic": { "avg": 1.6, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 1.8, "n": 3 }, "Programming": { "avg": 2.748, "n": 23 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 2.933, "n": 6 }, "Structured output": { "avg": 3.436, "n": 11 }, "Telco": { "avg": 3.85, "n": 8 } }, "dimensions": { "accuracy": 3.307, "completeness": 3.557, "clarity": 2.625, "domain_expertise": 3.295, "helpfulness": 2.932 }, "tokens_per_second": 31.7 }, { "name": "ornith-1.5:35b", "family": "qwen35moe", "params_b": 35.5, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 22616285024, "size_estimated": false, "installed": true, "min_memory_gb": 24.1, "overall": 3.552, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 4.4, "n": 1 }, "Classification - Few shot": { "avg": 3.58, "n": 10 }, "Classification - Zero shot": { "avg": 3.54, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 4.0, "n": 2 }, "Factography": { "avg": 2.5, "n": 2 }, "HR": { "avg": 2.8, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 3.3, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Logic": { "avg": 3.8, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 3.467, "n": 3 }, "Programming": { "avg": 3.2, "n": 23 }, "RAG": { "avg": 3.3, "n": 2 }, "Reasoning": { "avg": 4.4, "n": 1 }, "Role prompting": { "avg": 3.533, "n": 6 }, "Structured output": { "avg": 3.782, "n": 11 }, "Telco": { "avg": 4.25, "n": 8 } }, "dimensions": { "accuracy": 3.875, "completeness": 3.739, "clarity": 2.932, "domain_expertise": 3.841, "helpfulness": 3.375 }, "tokens_per_second": 132.4 }, { "name": "phi3.5:latest", "family": "phi3", "params_b": 3.8, "quantization": "Q4_0", "context_length": 131072, "size_bytes": 2137500000, "size_estimated": true, "installed": false, "min_memory_gb": 3.6, "overall": 2.185, "rated": 13, "failed": 18, "categories": { "Creative": { "avg": 2.8, "n": 1 }, "Education": { "avg": 2.4, "n": 2 }, "HR": { "avg": 1.6, "n": 1 }, "Health": { "avg": 1.8, "n": 1 }, "LLM": { "avg": 2.3, "n": 2 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Programming": { "avg": 1.7, "n": 2 }, "RAG": { "avg": 1.7, "n": 2 }, "Structured output": { "avg": 1.8, "n": 1 } }, "dimensions": { "accuracy": 2.154, "completeness": 2.385, "clarity": 2.077, "domain_expertise": 2.154, "helpfulness": 2.154 }, "tokens_per_second": 82.5 }, { "name": "phi3:latest", "family": "llama", "params_b": 4.0, "quantization": "Q4_K_M", "context_length": 4096, "size_bytes": 2318920898, "size_estimated": false, "installed": true, "min_memory_gb": 3.8, "overall": 2.437, "rated": 76, "failed": 12, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 1.9, "n": 10 }, "Classification - Zero shot": { "avg": 3.34, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 1.4, "n": 1 }, "HR": { "avg": 1.4, "n": 1 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 2.9, "n": 2 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 1.0, "n": 3 }, "Programming": { "avg": 1.971, "n": 21 }, "RAG": { "avg": 2.0, "n": 2 }, "Role prompting": { "avg": 1.0, "n": 6 }, "Structured output": { "avg": 3.333, "n": 9 }, "Telco": { "avg": 3.68, "n": 5 } }, "dimensions": { "accuracy": 2.276, "completeness": 2.513, "clarity": 3.053, "domain_expertise": 2.224, "helpfulness": 2.118 }, "tokens_per_second": 203.7 }, { "name": "phi3:medium", "family": "phi3", "params_b": 14.0, "quantization": "F16", "context_length": 4096, "size_bytes": 28000000000, "size_estimated": true, "installed": false, "min_memory_gb": 29.5, "overall": 2.676, "rated": 68, "failed": 12, "categories": { "Classification - Few shot": { "avg": 3.56, "n": 10 }, "Classification - Zero shot": { "avg": 2.9, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 2.8, "n": 2 }, "HR": { "avg": 2.2, "n": 1 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 3.7, "n": 2 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 1.0, "n": 3 }, "Programming": { "avg": 1.948, "n": 23 }, "RAG": { "avg": 1.8, "n": 2 }, "Structured output": { "avg": 3.35, "n": 8 }, "Telco": { "avg": 3.45, "n": 4 } }, "dimensions": { "accuracy": 2.588, "completeness": 2.706, "clarity": 3.221, "domain_expertise": 2.456, "helpfulness": 2.412 }, "tokens_per_second": 89.9 }, { "name": "phi4-mini-reasoning:latest", "family": "phi3", "params_b": 3.8, "quantization": "Q4_K_M", "context_length": 131072, "size_bytes": 3152479391, "size_estimated": false, "installed": true, "min_memory_gb": 4.7, "overall": 2.098, "rated": 102, "failed": 6, "categories": { "AI": { "avg": 3.2, "n": 1 }, "Classification - Few shot": { "avg": 2.2, "n": 10 }, "Classification - Zero shot": { "avg": 2.56, "n": 10 }, "Creative": { "avg": 3.2, "n": 1 }, "Education": { "avg": 3.0, "n": 2 }, "Factography": { "avg": 1.2, "n": 1 }, "HR": { "avg": 1.7, "n": 2 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 2.2, "n": 1 }, "Linux": { "avg": 2.8, "n": 1 }, "Logic": { "avg": 1.6, "n": 1 }, "Philosophy": { "avg": 2.6, "n": 1 }, "Polski": { "avg": 1.4, "n": 3 }, "Programming": { "avg": 1.703, "n": 33 }, "RAG": { "avg": 3.0, "n": 2 }, "Reasoning": { "avg": 3.2, "n": 1 }, "Role prompting": { "avg": 2.033, "n": 6 }, "Structured output": { "avg": 2.444, "n": 9 }, "Telco": { "avg": 3.067, "n": 6 }, "Terminal": { "avg": 1.52, "n": 10 } }, "dimensions": { "accuracy": 2.069, "completeness": 2.235, "clarity": 1.931, "domain_expertise": 2.265, "helpfulness": 1.99 }, "tokens_per_second": 158.7 }, { "name": "phi4-reasoning:latest", "family": "phi3", "params_b": 14.7, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 11117503233, "size_estimated": false, "installed": true, "min_memory_gb": 12.6, "overall": 3.639, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 3.2, "n": 1 }, "Classification - Few shot": { "avg": 3.8, "n": 10 }, "Classification - Zero shot": { "avg": 4.26, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.0, "n": 2 }, "Factography": { "avg": 2.0, "n": 2 }, "HR": { "avg": 3.8, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Linux": { "avg": 3.4, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 3.667, "n": 3 }, "Programming": { "avg": 3.209, "n": 23 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 3.3, "n": 6 }, "Structured output": { "avg": 3.982, "n": 11 }, "Telco": { "avg": 4.125, "n": 8 } }, "dimensions": { "accuracy": 3.966, "completeness": 3.724, "clarity": 3.391, "domain_expertise": 3.54, "helpfulness": 3.575 }, "tokens_per_second": 5.2 }, { "name": "phi4-reasoning:plus", "family": "phi3", "params_b": 14.7, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 9003750000, "size_estimated": true, "installed": false, "min_memory_gb": 10.5, "overall": 3.668, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.12, "n": 10 }, "Classification - Zero shot": { "avg": 4.28, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "Factography": { "avg": 1.6, "n": 2 }, "HR": { "avg": 3.8, "n": 2 }, "Health": { "avg": 3.0, "n": 1 }, "LLM": { "avg": 4.0, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Logic": { "avg": 3.0, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.467, "n": 3 }, "Programming": { "avg": 3.383, "n": 23 }, "RAG": { "avg": 3.5, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 3.5, "n": 6 }, "Structured output": { "avg": 3.964, "n": 11 }, "Telco": { "avg": 3.675, "n": 8 } }, "dimensions": { "accuracy": 4.102, "completeness": 3.739, "clarity": 3.295, "domain_expertise": 3.614, "helpfulness": 3.591 }, "tokens_per_second": 64.7 }, { "name": "phi4:latest", "family": "phi3", "params_b": 14.7, "quantization": "Q4_K_M", "context_length": 16384, "size_bytes": 9053116391, "size_estimated": false, "installed": true, "min_memory_gb": 10.6, "overall": 3.646, "rated": 82, "failed": 6, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 4.16, "n": 10 }, "Classification - Zero shot": { "avg": 4.1, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 1.6, "n": 1 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 3.8, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 1.933, "n": 3 }, "Programming": { "avg": 3.162, "n": 21 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 3.133, "n": 6 }, "Structured output": { "avg": 4.182, "n": 11 }, "Telco": { "avg": 4.0, "n": 7 } }, "dimensions": { "accuracy": 3.659, "completeness": 3.5, "clarity": 4.366, "domain_expertise": 3.305, "helpfulness": 3.415 }, "tokens_per_second": 77.1 }, { "name": "qwen2.5-coder:1.5b-base", "family": "qwen2", "params_b": 1.5, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 986060385, "size_estimated": false, "installed": true, "min_memory_gb": 2.5, "overall": 1.669, "rated": 75, "failed": 13, "categories": { "AI": { "avg": 2.8, "n": 1 }, "Classification - Few shot": { "avg": 1.08, "n": 10 }, "Classification - Zero shot": { "avg": 1.18, "n": 10 }, "Creative": { "avg": 2.0, "n": 1 }, "Education": { "avg": 1.6, "n": 2 }, "HR": { "avg": 1.0, "n": 1 }, "Health": { "avg": 2.0, "n": 1 }, "Linux": { "avg": 2.0, "n": 1 }, "Polski": { "avg": 1.0, "n": 3 }, "Programming": { "avg": 1.952, "n": 21 }, "RAG": { "avg": 1.9, "n": 2 }, "Reasoning": { "avg": 1.0, "n": 1 }, "Role prompting": { "avg": 1.0, "n": 6 }, "Structured output": { "avg": 2.275, "n": 8 }, "Telco": { "avg": 2.371, "n": 7 } }, "dimensions": { "accuracy": 1.533, "completeness": 1.627, "clarity": 1.973, "domain_expertise": 1.653, "helpfulness": 1.56 }, "tokens_per_second": 321.8 }, { "name": "qwen2.5-coder:14b", "family": "qwen2", "params_b": 14.8, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 8988124298, "size_estimated": false, "installed": true, "min_memory_gb": 10.5, "overall": 3.52, "rated": 80, "failed": 2, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 4.16, "n": 10 }, "Classification - Zero shot": { "avg": 4.02, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.0, "n": 2 }, "Factography": { "avg": 2.2, "n": 1 }, "HR": { "avg": 3.0, "n": 2 }, "Health": { "avg": 3.8, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 3.2, "n": 1 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 1.8, "n": 3 }, "Programming": { "avg": 3.07, "n": 23 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 2.0, "n": 1 }, "Structured output": { "avg": 4.164, "n": 11 }, "Telco": { "avg": 3.65, "n": 8 } }, "dimensions": { "accuracy": 3.45, "completeness": 3.35, "clarity": 4.45, "domain_expertise": 3.125, "helpfulness": 3.225 }, "tokens_per_second": 7.8 }, { "name": "qwen2.5-coder:32b", "family": "qwen2", "params_b": 32.8, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 20090000000, "size_estimated": true, "installed": false, "min_memory_gb": 21.6, "overall": 3.715, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 4.6, "n": 10 }, "Classification - Zero shot": { "avg": 4.48, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 2.1, "n": 2 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.6, "n": 2 }, "Linux": { "avg": 3.4, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.667, "n": 3 }, "Programming": { "avg": 3.348, "n": 23 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 2.633, "n": 6 }, "Structured output": { "avg": 3.964, "n": 11 }, "Telco": { "avg": 3.95, "n": 8 } }, "dimensions": { "accuracy": 3.667, "completeness": 3.632, "clarity": 4.46, "domain_expertise": 3.345, "helpfulness": 3.483 }, "tokens_per_second": 36.8 }, { "name": "qwen2.5-coder:3b", "family": "qwen2", "params_b": 3.1, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 1929912626, "size_estimated": false, "installed": true, "min_memory_gb": 3.4, "overall": 2.8, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 2.8, "n": 1 }, "Classification - Few shot": { "avg": 3.42, "n": 10 }, "Classification - Zero shot": { "avg": 3.02, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 2.9, "n": 2 }, "Factography": { "avg": 1.6, "n": 1 }, "HR": { "avg": 2.2, "n": 2 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 3.2, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 3.0, "n": 1 }, "Polski": { "avg": 1.467, "n": 3 }, "Programming": { "avg": 2.6, "n": 23 }, "RAG": { "avg": 3.2, "n": 2 }, "Reasoning": { "avg": 1.2, "n": 1 }, "Role prompting": { "avg": 1.567, "n": 6 }, "Structured output": { "avg": 3.655, "n": 11 }, "Telco": { "avg": 2.825, "n": 8 } }, "dimensions": { "accuracy": 2.581, "completeness": 2.791, "clarity": 3.779, "domain_expertise": 2.465, "helpfulness": 2.395 }, "tokens_per_second": 94.9 }, { "name": "qwen2.5-coder:7b", "family": "qwen2", "params_b": 7.6, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 4683087519, "size_estimated": false, "installed": true, "min_memory_gb": 6.2, "overall": 3.39, "rated": 80, "failed": 8, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 4.28, "n": 10 }, "Classification - Zero shot": { "avg": 4.24, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.1, "n": 2 }, "HR": { "avg": 3.0, "n": 1 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Polski": { "avg": 1.867, "n": 3 }, "Programming": { "avg": 2.852, "n": 23 }, "RAG": { "avg": 3.1, "n": 2 }, "Role prompting": { "avg": 2.2, "n": 6 }, "Structured output": { "avg": 3.727, "n": 11 }, "Telco": { "avg": 3.9, "n": 6 } }, "dimensions": { "accuracy": 3.275, "completeness": 3.3, "clarity": 4.213, "domain_expertise": 3.025, "helpfulness": 3.138 }, "tokens_per_second": 141.6 }, { "name": "qwen2.5:1.5b", "family": "qwen2", "params_b": 1.5, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 986061892, "size_estimated": false, "installed": true, "min_memory_gb": 2.5, "overall": 2.489, "rated": 74, "failed": 14, "categories": { "AI": { "avg": 2.6, "n": 1 }, "Classification - Few shot": { "avg": 3.26, "n": 10 }, "Classification - Zero shot": { "avg": 2.68, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 2.3, "n": 2 }, "HR": { "avg": 2.2, "n": 1 }, "Health": { "avg": 2.4, "n": 1 }, "LLM": { "avg": 3.4, "n": 2 }, "Philosophy": { "avg": 3.0, "n": 1 }, "Polski": { "avg": 1.2, "n": 3 }, "Programming": { "avg": 1.92, "n": 20 }, "RAG": { "avg": 2.7, "n": 2 }, "Role prompting": { "avg": 1.0, "n": 6 }, "Structured output": { "avg": 3.1, "n": 10 }, "Telco": { "avg": 3.85, "n": 4 } }, "dimensions": { "accuracy": 2.149, "completeness": 2.486, "clarity": 3.527, "domain_expertise": 2.149, "helpfulness": 2.135 }, "tokens_per_second": 336.1 }, { "name": "qwen2.5:3b", "family": "qwen2", "params_b": 3.1, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 1929912432, "size_estimated": false, "installed": true, "min_memory_gb": 3.4, "overall": 2.914, "rated": 79, "failed": 9, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 3.96, "n": 10 }, "Classification - Zero shot": { "avg": 3.66, "n": 10 }, "Creative": { "avg": 3.0, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Factography": { "avg": 1.4, "n": 1 }, "HR": { "avg": 2.6, "n": 1 }, "Health": { "avg": 3.0, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Polski": { "avg": 1.333, "n": 3 }, "Programming": { "avg": 2.191, "n": 22 }, "RAG": { "avg": 2.7, "n": 2 }, "Role prompting": { "avg": 1.3, "n": 6 }, "Structured output": { "avg": 3.7, "n": 10 }, "Telco": { "avg": 3.56, "n": 5 } }, "dimensions": { "accuracy": 2.709, "completeness": 3.025, "clarity": 3.658, "domain_expertise": 2.544, "helpfulness": 2.62 }, "tokens_per_second": 215.6 }, { "name": "qwen2.5:7b", "family": "qwen2", "params_b": 7.6, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 4683087332, "size_estimated": false, "installed": true, "min_memory_gb": 6.2, "overall": 3.407, "rated": 83, "failed": 5, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.28, "n": 10 }, "Classification - Zero shot": { "avg": 4.6, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "Factography": { "avg": 1.4, "n": 1 }, "HR": { "avg": 2.8, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.8, "n": 2 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.133, "n": 3 }, "Programming": { "avg": 2.6, "n": 23 }, "RAG": { "avg": 2.9, "n": 2 }, "Role prompting": { "avg": 2.067, "n": 6 }, "Structured output": { "avg": 3.927, "n": 11 }, "Telco": { "avg": 4.143, "n": 7 } }, "dimensions": { "accuracy": 3.277, "completeness": 3.446, "clarity": 4.072, "domain_expertise": 3.036, "helpfulness": 3.205 }, "tokens_per_second": 129.9 }, { "name": "qwen3-coder:30b", "family": "qwen3moe", "params_b": 30.5, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 18681250000, "size_estimated": true, "installed": false, "min_memory_gb": 20.2, "overall": 3.709, "rated": 86, "failed": 2, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 4.18, "n": 10 }, "Classification - Zero shot": { "avg": 4.64, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "Factography": { "avg": 1.4, "n": 1 }, "HR": { "avg": 3.5, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.9, "n": 2 }, "Linux": { "avg": 4.0, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.267, "n": 3 }, "Programming": { "avg": 3.243, "n": 23 }, "RAG": { "avg": 3.8, "n": 2 }, "Reasoning": { "avg": 1.6, "n": 1 }, "Role prompting": { "avg": 3.133, "n": 6 }, "Structured output": { "avg": 4.218, "n": 11 }, "Telco": { "avg": 4.075, "n": 8 } }, "dimensions": { "accuracy": 3.57, "completeness": 3.698, "clarity": 4.43, "domain_expertise": 3.314, "helpfulness": 3.535 }, "tokens_per_second": 131.4 }, { "name": "qwen3-coder:latest", "family": "qwen3moe", "params_b": 30.5, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 18681250000, "size_estimated": true, "installed": false, "min_memory_gb": 20.2, "overall": 3.881, "rated": 42, "failed": 2, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 4.4, "n": 2 }, "Linux": { "avg": 4.2, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 3.133, "n": 3 }, "Programming": { "avg": 3.275, "n": 8 }, "RAG": { "avg": 3.8, "n": 2 }, "Reasoning": { "avg": 3.0, "n": 1 }, "Structured output": { "avg": 4.273, "n": 11 }, "Telco": { "avg": 4.567, "n": 6 } }, "dimensions": { "accuracy": 3.881, "completeness": 3.762, "clarity": 4.667, "domain_expertise": 3.476, "helpfulness": 3.619 }, "tokens_per_second": 9.7 }, { "name": "qwen3-vl:8b", "family": "qwen3vl", "params_b": 8.8, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 6140415879, "size_estimated": false, "installed": true, "min_memory_gb": 7.6, "overall": 3.511, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.64, "n": 10 }, "Classification - Zero shot": { "avg": 4.24, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Factography": { "avg": 1.4, "n": 1 }, "HR": { "avg": 3.0, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.9, "n": 2 }, "Linux": { "avg": 4.0, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 1.8, "n": 3 }, "Programming": { "avg": 2.826, "n": 23 }, "RAG": { "avg": 3.5, "n": 2 }, "Reasoning": { "avg": 4.4, "n": 1 }, "Role prompting": { "avg": 2.5, "n": 6 }, "Structured output": { "avg": 3.68, "n": 10 }, "Telco": { "avg": 4.25, "n": 8 } }, "dimensions": { "accuracy": 3.306, "completeness": 3.647, "clarity": 4.129, "domain_expertise": 3.153, "helpfulness": 3.318 }, "tokens_per_second": 11.2 }, { "name": "qwen3.5:27b", "family": "qwen35", "params_b": 27.8, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 17027500000, "size_estimated": true, "installed": false, "min_memory_gb": 18.5, "overall": 3.941, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.7, "n": 10 }, "Classification - Zero shot": { "avg": 4.68, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 1.8, "n": 2 }, "HR": { "avg": 4.0, "n": 2 }, "Health": { "avg": 4.2, "n": 1 }, "LLM": { "avg": 4.3, "n": 2 }, "Linux": { "avg": 3.6, "n": 1 }, "Logic": { "avg": 3.8, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 3.6, "n": 3 }, "Programming": { "avg": 3.467, "n": 33 }, "RAG": { "avg": 4.0, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 3.967, "n": 6 }, "Structured output": { "avg": 4.455, "n": 11 }, "Telco": { "avg": 4.5, "n": 8 }, "Terminal": { "avg": 3.32, "n": 10 } }, "dimensions": { "accuracy": 3.833, "completeness": 4.074, "clarity": 4.389, "domain_expertise": 3.602, "helpfulness": 3.796 }, "tokens_per_second": 31.4 }, { "name": "qwen3.5:35b", "family": "qwen35moe", "params_b": 36.0, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 22050000000, "size_estimated": true, "installed": false, "min_memory_gb": 23.6, "overall": 3.752, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 4.4, "n": 1 }, "Classification - Few shot": { "avg": 4.58, "n": 10 }, "Classification - Zero shot": { "avg": 4.48, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 3.9, "n": 2 }, "Factography": { "avg": 1.4, "n": 2 }, "HR": { "avg": 3.8, "n": 2 }, "Health": { "avg": 3.8, "n": 1 }, "LLM": { "avg": 4.3, "n": 2 }, "Linux": { "avg": 2.8, "n": 1 }, "Logic": { "avg": 3.6, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 2.4, "n": 3 }, "Programming": { "avg": 3.026, "n": 23 }, "RAG": { "avg": 3.9, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 3.4, "n": 6 }, "Structured output": { "avg": 3.836, "n": 11 }, "Telco": { "avg": 4.7, "n": 8 } }, "dimensions": { "accuracy": 3.602, "completeness": 3.807, "clarity": 4.318, "domain_expertise": 3.455, "helpfulness": 3.591 }, "tokens_per_second": 27.8 }, { "name": "qwen3.5:4b", "family": "qwen35", "params_b": 4.7, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 3389983735, "size_estimated": false, "installed": true, "min_memory_gb": 4.9, "overall": 3.163, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.62, "n": 10 }, "Classification - Zero shot": { "avg": 4.7, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.9, "n": 2 }, "Factography": { "avg": 1.3, "n": 2 }, "HR": { "avg": 3.6, "n": 2 }, "Health": { "avg": 3.0, "n": 1 }, "LLM": { "avg": 4.1, "n": 2 }, "Linux": { "avg": 2.8, "n": 1 }, "Logic": { "avg": 1.0, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 2.8, "n": 3 }, "Programming": { "avg": 2.182, "n": 33 }, "RAG": { "avg": 3.9, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 2.467, "n": 6 }, "Structured output": { "avg": 3.982, "n": 11 }, "Telco": { "avg": 4.15, "n": 8 }, "Terminal": { "avg": 1.92, "n": 10 } }, "dimensions": { "accuracy": 2.981, "completeness": 3.389, "clarity": 3.546, "domain_expertise": 2.926, "helpfulness": 2.972 }, "tokens_per_second": 125.4 }, { "name": "qwen3.5:9b", "family": "qwen35", "params_b": 9.7, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 6594474711, "size_estimated": false, "installed": true, "min_memory_gb": 8.1, "overall": 3.505, "rated": 88, "failed": 0, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 4.42, "n": 10 }, "Classification - Zero shot": { "avg": 4.72, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "Factography": { "avg": 1.7, "n": 2 }, "HR": { "avg": 3.3, "n": 2 }, "Health": { "avg": 3.0, "n": 1 }, "LLM": { "avg": 4.1, "n": 2 }, "Linux": { "avg": 2.8, "n": 1 }, "Logic": { "avg": 1.4, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 1.867, "n": 3 }, "Programming": { "avg": 2.426, "n": 23 }, "RAG": { "avg": 3.9, "n": 2 }, "Reasoning": { "avg": 4.6, "n": 1 }, "Role prompting": { "avg": 3.033, "n": 6 }, "Structured output": { "avg": 4.164, "n": 11 }, "Telco": { "avg": 4.35, "n": 8 } }, "dimensions": { "accuracy": 3.341, "completeness": 3.659, "clarity": 4.045, "domain_expertise": 3.17, "helpfulness": 3.341 }, "tokens_per_second": 90.4 }, { "name": "qwen3.6:27b", "family": "qwen35", "params_b": 27.8, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 17420432739, "size_estimated": false, "installed": true, "min_memory_gb": 18.9, "overall": 4.094, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.0, "n": 1 }, "Classification - Few shot": { "avg": 4.64, "n": 10 }, "Classification - Zero shot": { "avg": 4.72, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 4.0, "n": 2 }, "Factography": { "avg": 1.8, "n": 2 }, "HR": { "avg": 3.6, "n": 2 }, "Health": { "avg": 4.6, "n": 1 }, "LLM": { "avg": 4.4, "n": 2 }, "Linux": { "avg": 4.4, "n": 1 }, "Logic": { "avg": 4.6, "n": 1 }, "Philosophy": { "avg": 4.4, "n": 1 }, "Polski": { "avg": 4.0, "n": 3 }, "Programming": { "avg": 3.703, "n": 33 }, "RAG": { "avg": 3.9, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 3.633, "n": 6 }, "Structured output": { "avg": 4.509, "n": 11 }, "Telco": { "avg": 4.65, "n": 8 }, "Terminal": { "avg": 3.94, "n": 10 } }, "dimensions": { "accuracy": 3.907, "completeness": 4.231, "clarity": 4.574, "domain_expertise": 3.75, "helpfulness": 4.009 }, "tokens_per_second": 21.7 }, { "name": "qwen3.6:35b", "family": "qwen35moe", "params_b": 36.0, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 23938333577, "size_estimated": false, "installed": true, "min_memory_gb": 25.4, "overall": 4.061, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.4, "n": 1 }, "Classification - Few shot": { "avg": 4.72, "n": 10 }, "Classification - Zero shot": { "avg": 4.66, "n": 10 }, "Creative": { "avg": 4.4, "n": 1 }, "Education": { "avg": 3.8, "n": 2 }, "Factography": { "avg": 2.0, "n": 2 }, "HR": { "avg": 3.9, "n": 2 }, "Health": { "avg": 4.4, "n": 1 }, "LLM": { "avg": 4.3, "n": 2 }, "Linux": { "avg": 4.0, "n": 1 }, "Logic": { "avg": 3.6, "n": 1 }, "Philosophy": { "avg": 5.0, "n": 1 }, "Polski": { "avg": 4.067, "n": 3 }, "Programming": { "avg": 3.661, "n": 33 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 4.4, "n": 1 }, "Role prompting": { "avg": 3.667, "n": 6 }, "Structured output": { "avg": 4.582, "n": 11 }, "Telco": { "avg": 4.55, "n": 8 }, "Terminal": { "avg": 3.74, "n": 10 } }, "dimensions": { "accuracy": 3.907, "completeness": 4.185, "clarity": 4.463, "domain_expertise": 3.778, "helpfulness": 3.972 }, "tokens_per_second": 95.4 }, { "name": "qwen3.8:27b", "family": "qwen35", "params_b": 27.3, "quantization": "Q4_K_M", "context_length": 262144, "size_bytes": 17741872154, "size_estimated": false, "installed": true, "min_memory_gb": 19.2, "overall": 4.169, "rated": 108, "failed": 0, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.38, "n": 10 }, "Classification - Zero shot": { "avg": 4.5, "n": 10 }, "Creative": { "avg": 4.2, "n": 1 }, "Education": { "avg": 4.1, "n": 2 }, "Factography": { "avg": 2.3, "n": 2 }, "HR": { "avg": 3.9, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 4.5, "n": 2 }, "Linux": { "avg": 3.6, "n": 1 }, "Logic": { "avg": 4.4, "n": 1 }, "Philosophy": { "avg": 4.8, "n": 1 }, "Polski": { "avg": 4.4, "n": 3 }, "Programming": { "avg": 3.848, "n": 33 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 3.867, "n": 6 }, "Structured output": { "avg": 4.564, "n": 11 }, "Telco": { "avg": 4.775, "n": 8 }, "Terminal": { "avg": 4.26, "n": 10 } }, "dimensions": { "accuracy": 3.861, "completeness": 4.426, "clarity": 4.611, "domain_expertise": 3.87, "helpfulness": 4.074 }, "tokens_per_second": 55.6 }, { "name": "qwen3:1.7b", "family": "qwen3", "params_b": 2.0, "quantization": "Q4_K_M", "context_length": 40960, "size_bytes": 1359293444, "size_estimated": false, "installed": true, "min_memory_gb": 2.9, "overall": 2.681, "rated": 99, "failed": 9, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 3.48, "n": 10 }, "Classification - Zero shot": { "avg": 3.12, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Health": { "avg": 2.8, "n": 1 }, "LLM": { "avg": 2.7, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 1.867, "n": 3 }, "Programming": { "avg": 2.169, "n": 32 }, "RAG": { "avg": 3.3, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 1.867, "n": 6 }, "Structured output": { "avg": 3.636, "n": 11 }, "Telco": { "avg": 3.68, "n": 5 }, "Terminal": { "avg": 1.54, "n": 10 } }, "dimensions": { "accuracy": 2.303, "completeness": 2.859, "clarity": 3.465, "domain_expertise": 2.283, "helpfulness": 2.475 }, "tokens_per_second": 252.5 }, { "name": "qwen3:14b", "family": "qwen3", "params_b": 14.8, "quantization": "Q4_K_M", "context_length": 40960, "size_bytes": 9276198565, "size_estimated": false, "installed": true, "min_memory_gb": 10.8, "overall": 3.792, "rated": 106, "failed": 2, "categories": { "AI": { "avg": 4.6, "n": 1 }, "Classification - Few shot": { "avg": 4.64, "n": 10 }, "Classification - Zero shot": { "avg": 4.74, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.7, "n": 2 }, "Factography": { "avg": 2.0, "n": 1 }, "HR": { "avg": 3.7, "n": 2 }, "Health": { "avg": 3.8, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 3.0, "n": 1 }, "Philosophy": { "avg": 4.2, "n": 1 }, "Polski": { "avg": 3.667, "n": 3 }, "Programming": { "avg": 3.242, "n": 33 }, "RAG": { "avg": 3.7, "n": 2 }, "Reasoning": { "avg": 4.2, "n": 1 }, "Role prompting": { "avg": 3.433, "n": 6 }, "Structured output": { "avg": 4.309, "n": 11 }, "Telco": { "avg": 4.35, "n": 8 }, "Terminal": { "avg": 3.24, "n": 10 } }, "dimensions": { "accuracy": 3.708, "completeness": 3.906, "clarity": 4.198, "domain_expertise": 3.453, "helpfulness": 3.698 }, "tokens_per_second": 66.5 }, { "name": "qwen3:30b", "family": "qwen3moe", "params_b": 30.5, "quantization": "Q4_K_M", "context_length": 40960, "size_bytes": 18681250000, "size_estimated": true, "installed": false, "min_memory_gb": 20.2, "overall": 3.876, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 4.2, "n": 1 }, "Classification - Few shot": { "avg": 4.68, "n": 10 }, "Classification - Zero shot": { "avg": 4.74, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Factography": { "avg": 1.5, "n": 2 }, "HR": { "avg": 3.3, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 3.7, "n": 2 }, "Linux": { "avg": 3.4, "n": 1 }, "Logic": { "avg": 3.4, "n": 1 }, "Philosophy": { "avg": 4.0, "n": 1 }, "Polski": { "avg": 3.667, "n": 3 }, "Programming": { "avg": 3.278, "n": 23 }, "RAG": { "avg": 4.0, "n": 2 }, "Reasoning": { "avg": 4.2, "n": 1 }, "Role prompting": { "avg": 3.533, "n": 6 }, "Structured output": { "avg": 4.2, "n": 10 }, "Telco": { "avg": 4.35, "n": 8 } }, "dimensions": { "accuracy": 3.828, "completeness": 4.023, "clarity": 4.161, "domain_expertise": 3.552, "helpfulness": 3.805 }, "tokens_per_second": 36.9 }, { "name": "qwen3:32b", "family": "qwen3", "params_b": 32.8, "quantization": "Q4_K_M", "context_length": 40960, "size_bytes": 20090000000, "size_estimated": true, "installed": false, "min_memory_gb": 21.6, "overall": 3.924, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 4.58, "n": 10 }, "Classification - Zero shot": { "avg": 4.76, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "Factography": { "avg": 1.9, "n": 2 }, "HR": { "avg": 3.4, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 3.9, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Philosophy": { "avg": 4.8, "n": 1 }, "Polski": { "avg": 3.467, "n": 3 }, "Programming": { "avg": 3.513, "n": 23 }, "RAG": { "avg": 3.5, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 3.5, "n": 6 }, "Structured output": { "avg": 3.927, "n": 11 }, "Telco": { "avg": 4.45, "n": 8 } }, "dimensions": { "accuracy": 3.897, "completeness": 4.034, "clarity": 4.23, "domain_expertise": 3.586, "helpfulness": 3.874 }, "tokens_per_second": 2.4 }, { "name": "qwen3:4b", "family": "qwen3", "params_b": 4.0, "quantization": "Q4_K_M", "context_length": 40960, "size_bytes": 2620788260, "size_estimated": false, "installed": true, "min_memory_gb": 4.1, "overall": 3.482, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 3.8, "n": 1 }, "Classification - Few shot": { "avg": 4.16, "n": 10 }, "Classification - Zero shot": { "avg": 4.16, "n": 10 }, "Creative": { "avg": 4.0, "n": 1 }, "Education": { "avg": 3.5, "n": 2 }, "Factography": { "avg": 1.3, "n": 2 }, "HR": { "avg": 2.6, "n": 2 }, "Health": { "avg": 4.0, "n": 1 }, "LLM": { "avg": 3.6, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 3.133, "n": 3 }, "Programming": { "avg": 2.827, "n": 22 }, "RAG": { "avg": 3.3, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 2.7, "n": 6 }, "Structured output": { "avg": 4.182, "n": 11 }, "Telco": { "avg": 4.057, "n": 7 } }, "dimensions": { "accuracy": 3.318, "completeness": 3.671, "clarity": 3.929, "domain_expertise": 3.106, "helpfulness": 3.388 }, "tokens_per_second": 85.2 }, { "name": "qwen3:8b", "family": "qwen3", "params_b": 8.2, "quantization": "Q4_K_M", "context_length": 40960, "size_bytes": 5225388164, "size_estimated": false, "installed": true, "min_memory_gb": 6.7, "overall": 3.623, "rated": 87, "failed": 1, "categories": { "AI": { "avg": 4.4, "n": 1 }, "Classification - Few shot": { "avg": 4.16, "n": 10 }, "Classification - Zero shot": { "avg": 4.4, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.6, "n": 2 }, "Factography": { "avg": 1.6, "n": 2 }, "HR": { "avg": 3.0, "n": 2 }, "Health": { "avg": 3.6, "n": 1 }, "LLM": { "avg": 2.8, "n": 2 }, "Linux": { "avg": 3.8, "n": 1 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 3.333, "n": 3 }, "Programming": { "avg": 3.078, "n": 23 }, "RAG": { "avg": 2.8, "n": 2 }, "Reasoning": { "avg": 4.0, "n": 1 }, "Role prompting": { "avg": 3.333, "n": 6 }, "Structured output": { "avg": 3.964, "n": 11 }, "Telco": { "avg": 4.275, "n": 8 } }, "dimensions": { "accuracy": 3.563, "completeness": 3.678, "clarity": 4.057, "domain_expertise": 3.322, "helpfulness": 3.506 }, "tokens_per_second": 55.4 }, { "name": "smollm:latest", "family": "llama", "params_b": 1.7, "quantization": "Q4_0", "context_length": 2048, "size_bytes": 990741362, "size_estimated": false, "installed": true, "min_memory_gb": 2.5, "overall": 1.652, "rated": 66, "failed": 22, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 1.1, "n": 10 }, "Classification - Zero shot": { "avg": 1.08, "n": 10 }, "Creative": { "avg": 3.4, "n": 1 }, "Education": { "avg": 2.9, "n": 2 }, "HR": { "avg": 1.2, "n": 1 }, "Health": { "avg": 2.0, "n": 1 }, "LLM": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 2.4, "n": 1 }, "Polski": { "avg": 1.067, "n": 3 }, "Programming": { "avg": 1.67, "n": 20 }, "RAG": { "avg": 1.8, "n": 1 }, "Role prompting": { "avg": 2.0, "n": 6 }, "Structured output": { "avg": 1.4, "n": 5 }, "Telco": { "avg": 3.067, "n": 3 } }, "dimensions": { "accuracy": 1.621, "completeness": 1.439, "clarity": 2.212, "domain_expertise": 1.53, "helpfulness": 1.455 }, "tokens_per_second": 391.4 }, { "name": "speakleash/bielik-1.5b-v3.0-instruct:Q8_0", "family": "llama", "params_b": 1.6, "quantization": "Q8_0", "context_length": 8192, "size_bytes": 1699569076, "size_estimated": false, "installed": true, "min_memory_gb": 3.2, "overall": 1.532, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 2.6, "n": 1 }, "Classification - Few shot": { "avg": 1.14, "n": 10 }, "Classification - Zero shot": { "avg": 1.06, "n": 10 }, "Creative": { "avg": 1.2, "n": 1 }, "Education": { "avg": 2.9, "n": 2 }, "HR": { "avg": 1.5, "n": 2 }, "Health": { "avg": 1.0, "n": 1 }, "LLM": { "avg": 1.9, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 1.8, "n": 1 }, "Polski": { "avg": 1.067, "n": 3 }, "Programming": { "avg": 1.2, "n": 23 }, "RAG": { "avg": 1.6, "n": 2 }, "Reasoning": { "avg": 1.2, "n": 1 }, "Role prompting": { "avg": 2.567, "n": 6 }, "Structured output": { "avg": 2.255, "n": 11 }, "Telco": { "avg": 1.425, "n": 8 } }, "dimensions": { "accuracy": 1.506, "completeness": 1.447, "clarity": 1.965, "domain_expertise": 1.424, "helpfulness": 1.318 }, "tokens_per_second": 279.0 }, { "name": "speakleash/bielik-11b-v2.3-instruct:Q4_K_M", "family": "llama", "params_b": 11.2, "quantization": "Q4_K_M", "context_length": 32768, "size_bytes": 6860000000, "size_estimated": true, "installed": false, "min_memory_gb": 8.4, "overall": 3.033, "rated": 79, "failed": 1, "categories": { "AI": { "avg": 3.6, "n": 1 }, "Classification - Few shot": { "avg": 3.66, "n": 10 }, "Classification - Zero shot": { "avg": 3.72, "n": 10 }, "Creative": { "avg": 3.6, "n": 1 }, "Education": { "avg": 3.0, "n": 2 }, "HR": { "avg": 2.6, "n": 2 }, "Health": { "avg": 3.2, "n": 1 }, "LLM": { "avg": 2.4, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 3.4, "n": 1 }, "Polski": { "avg": 2.467, "n": 3 }, "Programming": { "avg": 2.183, "n": 23 }, "RAG": { "avg": 3.6, "n": 2 }, "Reasoning": { "avg": 1.6, "n": 1 }, "Structured output": { "avg": 3.709, "n": 11 }, "Telco": { "avg": 3.325, "n": 8 } }, "dimensions": { "accuracy": 3.165, "completeness": 2.81, "clarity": 3.684, "domain_expertise": 2.861, "helpfulness": 2.633 }, "tokens_per_second": 94.6 }, { "name": "speakleash/bielik-11b-v3.0-instruct:Q6_K", "family": "llama", "params_b": 11.2, "quantization": "Q6_K", "context_length": 32768, "size_bytes": 9163970529, "size_estimated": false, "installed": true, "min_memory_gb": 10.7, "overall": 3.139, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 3.2, "n": 1 }, "Classification - Few shot": { "avg": 3.36, "n": 10 }, "Classification - Zero shot": { "avg": 3.72, "n": 10 }, "Creative": { "avg": 3.2, "n": 1 }, "Education": { "avg": 3.4, "n": 2 }, "HR": { "avg": 3.5, "n": 2 }, "Health": { "avg": 3.4, "n": 1 }, "LLM": { "avg": 3.5, "n": 2 }, "Linux": { "avg": 2.4, "n": 1 }, "Philosophy": { "avg": 3.8, "n": 1 }, "Polski": { "avg": 1.733, "n": 3 }, "Programming": { "avg": 2.452, "n": 23 }, "RAG": { "avg": 3.4, "n": 2 }, "Reasoning": { "avg": 4.8, "n": 1 }, "Role prompting": { "avg": 3.5, "n": 6 }, "Structured output": { "avg": 3.909, "n": 11 }, "Telco": { "avg": 2.75, "n": 8 } }, "dimensions": { "accuracy": 3.153, "completeness": 3.047, "clarity": 3.847, "domain_expertise": 2.918, "helpfulness": 2.729 }, "tokens_per_second": 69.9 }, { "name": "speakleash/bielik-4.5b-v3.0-instruct:Q8_0", "family": "llama", "params_b": 4.8, "quantization": "Q8_0", "context_length": 8192, "size_bytes": 5061216212, "size_estimated": false, "installed": true, "min_memory_gb": 6.6, "overall": 2.216, "rated": 85, "failed": 3, "categories": { "AI": { "avg": 3.4, "n": 1 }, "Classification - Few shot": { "avg": 1.3, "n": 10 }, "Classification - Zero shot": { "avg": 1.86, "n": 10 }, "Creative": { "avg": 3.8, "n": 1 }, "Education": { "avg": 3.3, "n": 2 }, "HR": { "avg": 2.2, "n": 2 }, "Health": { "avg": 3.0, "n": 1 }, "LLM": { "avg": 3.4, "n": 2 }, "Linux": { "avg": 2.2, "n": 1 }, "Philosophy": { "avg": 2.6, "n": 1 }, "Polski": { "avg": 1.667, "n": 3 }, "Programming": { "avg": 1.913, "n": 23 }, "RAG": { "avg": 1.5, "n": 2 }, "Reasoning": { "avg": 1.8, "n": 1 }, "Role prompting": { "avg": 2.7, "n": 6 }, "Structured output": { "avg": 2.855, "n": 11 }, "Telco": { "avg": 2.825, "n": 8 } }, "dimensions": { "accuracy": 2.165, "completeness": 2.153, "clarity": 2.906, "domain_expertise": 1.976, "helpfulness": 1.894 }, "tokens_per_second": 113.5 }, { "name": "tinyllama:latest", "family": "llama", "params_b": 1.0, "quantization": "Q4_0", "context_length": 2048, "size_bytes": 637700138, "size_estimated": false, "installed": true, "min_memory_gb": 2.1, "overall": 1.302, "rated": 51, "failed": 37, "categories": { "AI": { "avg": 2.4, "n": 1 }, "Classification - Few shot": { "avg": 1.06, "n": 10 }, "Classification - Zero shot": { "avg": 1.1, "n": 10 }, "Creative": { "avg": 3.0, "n": 1 }, "Education": { "avg": 1.7, "n": 2 }, "Programming": { "avg": 1.227, "n": 15 }, "RAG": { "avg": 2.2, "n": 1 }, "Role prompting": { "avg": 1.333, "n": 6 }, "Structured output": { "avg": 1.48, "n": 5 } }, "dimensions": { "accuracy": 1.216, "completeness": 1.275, "clarity": 1.686, "domain_expertise": 1.176, "helpfulness": 1.157 }, "tokens_per_second": 489.4 } ] }