models

Open-weight models currently being discussed. Each entry links to its Hugging Face page plus the community threads we've grouped together. Proprietary models (Claude, GPT, Cursor, etc.) are tracked as threads but don't appear here.

• Qwen3-0.6B Qwen/Qwen3-0.6B 15189206 dl 7 threads
• gpt2 openai-community/gpt2 13784271 dl 2 threads
• Qwen2.5-1.5B-Instruct Qwen/Qwen2.5-1.5B-Instruct 13065099 dl 1 thread
• Qwen2.5-7B-Instruct Qwen/Qwen2.5-7B-Instruct 12506262 dl 4 threads
• gemma-4-26B-A4B-it google/gemma-4-26B-A4B-it 11696495 dl 1 thread
• DeepSeek-V3.2 deepseek-ai/DeepSeek-V3.2 10654004 dl 3 threads
• Qwen3.5-4B Qwen/Qwen3.5-4B 10156913 dl 1 thread
• Llama-3.1-8B-Instruct meta-llama/Llama-3.1-8B-Instruct 9393753 dl 1 thread
• Llama-3.2-1B-Instruct meta-llama/Llama-3.2-1B-Instruct 7743597 dl 1 thread
• Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B 5910215 dl 1 thread
• Qwen3.5-9B Qwen/Qwen3.5-9B 5662081 dl 1 thread
• Meta-Llama-3-8B meta-llama/Meta-Llama-3-8B 3449490 dl 1 thread
• gemma-4-31B-it google/gemma-4-31B-it 2640636 dl 2 threads
• gemma-3-12b-it google/gemma-3-12b-it 2515706 dl 2 threads
• GLM-5.1-FP8 zai-org/GLM-5.1-FP8 1170968 dl 1 thread
• DeepSeek-V3 deepseek-ai/DeepSeek-V3 1045642 dl 1 thread
• Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF 932188 dl 6 threads
• Llama-3.3-70B-Instruct meta-llama/Llama-3.3-70B-Instruct 867836 dl 1 thread
• GLM-4.7-Flash zai-org/GLM-4.7-Flash 675117 dl 3 threads
• GLM-5 zai-org/GLM-5 442542 dl 1 thread
• Llama-4-Scout-17B-16E-Instruct meta-llama/Llama-4-Scout-17B-16E-Instruct 389687 dl 1 thread
• Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled 182091 dl 1 thread
• GLM-5.1 zai-org/GLM-5.1 84784 dl 4 threads
• DeepSeek-V4-Pro deepseek-ai/DeepSeek-V4-Pro 78864 dl 2 threads
• MiniMax-M2.7 MiniMaxAI/MiniMax-M2.7 43645 dl 2 threads