GGUF models by ijohn07
106 GGUF models quantized by ijohn07 on Hugging Face. Sizes run from 773M to 34.7B parameters. The longest trained context is 1024K tokens.
About ijohn07 on Hugging Face
ijohn07 has published 106 GGUF models that ggufmodels.com tracks, across families such as DeepSeek, Mistral and Qwen. The most downloaded are Qwen3 14B Uncensored, Harness 1 and Qwen3 Coder 30B A3B Instruct FP8.
The quants ijohn07 publishes most often are Q8_0 (50), Q4_K_M (25), Q6_K (16) and Q2_K (6). Their Q4_K_M files range from 0.7 to 21.2 GB. Parameter counts run from 773M to 34.7B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has ijohn07 published?
106 models are listed here, mainly from the DeepSeek, Mistral and Qwen families. The most downloaded is Qwen3 14B Uncensored.
Which quants does ijohn07 publish?
The most common are Q8_0 (50 models), Q4_K_M (25 models), Q6_K (16 models) and Q2_K (6 models).