GGUF models by llmfan46
97 GGUF models quantized by llmfan46 on Hugging Face. Sizes run from 447M to 426B parameters. The longest trained context is 1024K tokens.
About llmfan46 on Hugging Face
llmfan46 has published 97 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Omega. The most downloaded are Gemma 4 E4B It Ultra Uncensored Heretic, Qwen3.6 35B A3B Uncensored Heretic Native MTP Preserved and Gemma 4 31B It Uncensored Heretic.
The quants llmfan46 publishes most often are Q8_0 (87), BF16 (79), Q6_K (77) and Q5_K_S (77). Their Q4_K_M files range from 3.4 to 258.0 GB. Parameter counts run from 447M to 426B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has llmfan46 published?
97 models are listed here, mainly from the Qwen, Gemma and Omega families. The most downloaded is Gemma 4 E4B It Ultra Uncensored Heretic.
Which quants does llmfan46 publish?
The most common are Q8_0 (87 models), BF16 (79 models), Q6_K (77 models) and Q5_K_S (77 models).