GGUF models by dranger003
46 GGUF models quantized by dranger003 on Hugging Face. Sizes run from 2.77B to 132B parameters. The longest trained context is 1024K tokens.
About dranger003 on Hugging Face
dranger003 has published 46 GGUF models that ggufmodels.com tracks, across families such as Mistral, Bagel and StarCoder. The most downloaded are c4ai-command-r-plus, dbrx instruct iMat and c4ai-command-r-v01.
The quants dranger003 publishes most often are Q8_0 (31), IQ3_XXS (28), IQ2_XS (22) and IQ2_XXS (20). Their Q4_K_M files range from 4.1 to 62.8 GB. Parameter counts run from 2.77B to 132B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has dranger003 published?
46 models are listed here, mainly from the Mistral, Bagel and StarCoder families. The most downloaded is c4ai-command-r-plus.
Which quants does dranger003 publish?
The most common are Q8_0 (31 models), IQ3_XXS (28 models), IQ2_XS (22 models) and IQ2_XXS (20 models).