GGUF models by Cran-May
92 GGUF models quantized by Cran-May on Hugging Face. Sizes run from 66M to 72.7B parameters. The longest trained context is 1000K tokens.
About Cran-May on Hugging Face
Cran-May has published 92 GGUF models that ggufmodels.com tracks, across families such as Mistral, Llama and Qwen. The most downloaded are OpenBuddy R10528DistillQwen 72B Preview1, Replete Qwen 2.5 3b CoT RP Q5 K M and XinYuan Qwen2.5 7B 0917 Q4 K M.
The quants Cran-May publishes most often are Q4_K_M (34), Q5_K_M (26), Q4_K_S (9) and IQ4_XS (7). Their Q4_K_M files range from 1.1 to 42.5 GB. Parameter counts run from 66M to 72.7B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has Cran-May published?
92 models are listed here, mainly from the Mistral, Llama and Qwen families. The most downloaded is OpenBuddy R10528DistillQwen 72B Preview1.
Which quants does Cran-May publish?
The most common are Q4_K_M (34 models), Q5_K_M (26 models), Q4_K_S (9 models) and IQ4_XS (7 models).