GGUF models by professorf
55 GGUF models quantized by professorf on Hugging Face. Sizes run from 135M to 70.6B parameters. The longest trained context is 1024K tokens.
About professorf on Hugging Face
professorf has published 55 GGUF models that ggufmodels.com tracks, across families such as Llama, Mistral and SmolLM. The most downloaded are Gemma 4 26B A4B It, Dolphin Mistral 24B Venice Edition and Gemma 4 12B It.
The quants professorf publishes most often are Q8_0 (43), Q6_K (23), Q5_K_M (23) and Q4_K_M (23). Their Q4_K_M files range from 0.8 to 42.5 GB. Parameter counts run from 135M to 70.6B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has professorf published?
55 models are listed here, mainly from the Llama, Mistral and SmolLM families. The most downloaded is Gemma 4 26B A4B It.
Which quants does professorf publish?
The most common are Q8_0 (43 models), Q6_K (23 models), Q5_K_M (23 models) and Q4_K_M (23 models).