GGUF models by CHE-72
86 GGUF models quantized by CHE-72 on Hugging Face. Sizes run from 494M to 14B parameters. The longest trained context is 128K tokens.
About CHE-72 on Hugging Face
CHE-72 has published 86 GGUF models that ggufmodels.com tracks, across families such as Qwen, Yi and Taide. The most downloaded are Breeze-7B-Instruct-v1_0, Qwen1.5-4B-Chat and Phi 3 mini 128k instruct Q6 K.
The quants CHE-72 publishes most often are Q8_0 (10), Q6_K (10), Q5_K_M (7) and Q5_0 (7). Their Q4_K_M files range from 2.5 to 8.6 GB. Parameter counts run from 494M to 14B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has CHE-72 published?
86 models are listed here, mainly from the Qwen, Yi and Taide families. The most downloaded is Breeze-7B-Instruct-v1_0.
Which quants does CHE-72 publish?
The most common are Q8_0 (10 models), Q6_K (10 models), Q5_K_M (7 models) and Q5_0 (7 models).