GGUF models by Mathieu-Thomas-JOSSET
75 GGUF models quantized by Mathieu-Thomas-JOSSET on Hugging Face. Sizes run from 596M to 23.6B parameters. The longest trained context is 128K tokens.
About Mathieu-Thomas-JOSSET on Hugging Face
Mathieu-Thomas-JOSSET has published 75 GGUF models that ggufmodels.com tracks, across families such as Phi, Qwen and Gemma. The most downloaded are gemma 3n text gguf3, joke finetome model gguf phi4 20260111 025151 and joke finetome model gguf phi4 20260111 113458.
The quants Mathieu-Thomas-JOSSET publishes most often are Q8_0 (38), Q4_K_M (37) and BF16 (6). Their Q4_K_M files range from 0.8 to 14.3 GB. Parameter counts run from 596M to 23.6B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has Mathieu-Thomas-JOSSET published?
75 models are listed here, mainly from the Phi, Qwen and Gemma families. The most downloaded is gemma 3n text gguf3.
Which quants does Mathieu-Thomas-JOSSET publish?
The most common are Q8_0 (38 models), Q4_K_M (37 models) and BF16 (6 models).