GGUF models by RichardErkhov
14354 GGUF models quantized by RichardErkhov on Hugging Face. Sizes run from 1M to 316B parameters. The longest trained context is 102400K tokens.
About RichardErkhov on Hugging Face
RichardErkhov has published 14,354 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Mistral. The most downloaded are Topxtral-4x7B-v0.1, SeaLLMs SeaLLMs v3 7B Chat and Jiqing tiny random falcon.
The quants RichardErkhov publishes most often are Q2_K (14352), Q3_K_S (14059), Q3_K (13884) and Q3_K_M (13868). Their Q4_K_M files range from 0.0 to 129.1 GB. Parameter counts run from 1M to 316B, and the longest trained context window is 102400K tokens.
Frequently asked questions
What GGUF models has RichardErkhov published?
14,354 models are listed here, mainly from the Llama, Qwen and Mistral families. The most downloaded is Topxtral-4x7B-v0.1.
Which quants does RichardErkhov publish?
The most common are Q2_K (14352 models), Q3_K_S (14059 models), Q3_K (13884 models) and Q3_K_M (13868 models).