GGUF models by HyzeAI
37 GGUF models quantized by HyzeAI on Hugging Face. Sizes run from 135M to 30.5B parameters. The longest trained context is 256K tokens.
About HyzeAI on Hugging Face
HyzeAI has published 37 GGUF models that ggufmodels.com tracks, across families such as Hyzemini, Hyzeqweninstruct and Llama. The most downloaded are Hyze1BInstruct, HyzeMini V2 and HyzeQwenInstruct.
The quants HyzeAI publishes most often are Q8_0 (5), Q6_K (5), Q5_K_M (5) and Q4_K_M (5). Their Q4_K_M files range from 0.1 to 18.6 GB. Parameter counts run from 135M to 30.5B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has HyzeAI published?
37 models are listed here, mainly from the Hyzemini, Hyzeqweninstruct and Llama families. The most downloaded is Hyze1BInstruct.
Which quants does HyzeAI publish?
The most common are Q8_0 (5 models), Q6_K (5 models), Q5_K_M (5 models) and Q4_K_M (5 models).