Coding GGUF models
14916 GGUF models: models tuned for programming and code completion. Sizes run from 1M to 1780B parameters. The longest trained context is 3906K tokens.
About Coding GGUF models
14,916 GGUF models are filed under Coding: models tuned for programming and code completion. The most downloaded are Tiel Coder 35B A3B GGUF MTP, Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP and Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP. Parameter counts run from 1M to 1780B, and the longest trained context window is 3906K tokens.
For code, quantization errors can break syntax, so many people choose Q5_K_M or higher when memory allows. The families you will see most are Qwen (4387), Llama (1259) and Phi (862).
Frequently asked questions
What are Coding GGUF models?
Models tuned for programming and code completion. There are 14,916 of them on this site.
Which Coding GGUF model should I start with?
The most downloaded is Tiel Coder 35B A3B GGUF MTP. Choose the size that fits your GPU, then a Q4_K_M quant unless you have memory to spare.