Reasoning GGUF models
46569 GGUF models: models that think step by step before answering. Sizes run from 1M to 5376B parameters. The longest trained context is 5120K tokens.
About Reasoning GGUF models
46,569 GGUF models are filed under Reasoning: models that think step by step before answering. The most downloaded are Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP, Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP and Swift 1.5 Qwen3.8 27B GSQ RCO. Parameter counts run from 1M to 5376B, and the longest trained context window is 5120K tokens.
Reasoning models write long chains of thought before the answer, so a larger context window and faster generation matter more than usual. The families you will see most are Qwen (17571), Gemma (3426) and DeepSeek (2899).
Frequently asked questions
What are Reasoning GGUF models?
Models that think step by step before answering. There are 46,569 of them on this site.
Which Reasoning GGUF model should I start with?
The most downloaded is Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP. Choose the size that fits your GPU, then a Q4_K_M quant unless you have memory to spare.