GGUF models by Azure99
40 GGUF models quantized by Azure99 on Hugging Face. Sizes run from 1.84B to 36.2B parameters. The longest trained context is 512K tokens.
About Azure99 on Hugging Face
Azure99 has published 40 GGUF models that ggufmodels.com tracks, across families such as Blossom, Qwen and Yi. The most downloaded are Blossom V7.1 27B, Blossom V6.4 27B and Blossom V6.4 9B.
The quants Azure99 publishes most often are Q6_K (40), Q5_K_S (40), Q5_K_M (40) and Q4_K_S (40). Their Q4_K_M files range from 1.2 to 21.8 GB. Parameter counts run from 1.84B to 36.2B, and the longest trained context window is 512K tokens.
Frequently asked questions
What GGUF models has Azure99 published?
40 models are listed here, mainly from the Blossom, Qwen and Yi families. The most downloaded is Blossom V7.1 27B.
Which quants does Azure99 publish?
The most common are Q6_K (40 models), Q5_K_S (40 models), Q5_K_M (40 models) and Q4_K_S (40 models).