GGUF models by burningfeet
55 GGUF models quantized by burningfeet on Hugging Face. Sizes run from 596M to 35.5B parameters. The longest trained context is 256K tokens.
About burningfeet on Hugging Face
burningfeet has published 55 GGUF models that ggufmodels.com tracks, across families such as Qwen, Ornith and Gemma. The most downloaded are backup2026 09 20 mudler Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled APEX, Qwen3.6 35B A3B Uncensored Genesis Hermes V5 and backup 2026 09 12 ERRONEOUS Qwen3.6 35B A3B Uncensored Genesis Hermes Final.
The quants burningfeet publishes most often are Q8_K (38), Q8_0 (10), Q4_K_M (6) and Q6_K (5). Their Q4_K_M files range from 5.3 to 17.6 GB. Parameter counts run from 596M to 35.5B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has burningfeet published?
55 models are listed here, mainly from the Qwen, Ornith and Gemma families. The most downloaded is backup2026 09 20 mudler Qwen3.6 35B A3B Claude 4.7 Opus Reasoning Distilled APEX.
Which quants does burningfeet publish?
The most common are Q8_K (38 models), Q8_0 (10 models), Q4_K_M (6 models) and Q6_K (5 models).