GGUF models by QuantFactory
1418 GGUF models quantized by QuantFactory on Hugging Face. Sizes run from 9M to 225B parameters. The longest trained context is 4194304K tokens.
About QuantFactory on Hugging Face
QuantFactory has published 1,418 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Mistral. The most downloaded are Meta Llama 3 8B Instruct, Qwen2.5 7B Instruct abliterated v2 and Glm 4 9b Chat.
The quants QuantFactory publishes most often are Q4_K_M (1415), Q4_0 (1407), Q8_0 (1404) and Q6_K (1399). Their Q4_K_M files range from 0.0 to 134.8 GB. Parameter counts run from 9M to 225B, and the longest trained context window is 4194304K tokens.
Frequently asked questions
What GGUF models has QuantFactory published?
1,418 models are listed here, mainly from the Llama, Qwen and Mistral families. The most downloaded is Meta Llama 3 8B Instruct.
Which quants does QuantFactory publish?
The most common are Q4_K_M (1415 models), Q4_0 (1407 models), Q8_0 (1404 models) and Q6_K (1399 models).