GGUF models by YOYO-AI
60 GGUF models quantized by YOYO-AI on Hugging Face. Sizes run from 4.02B to 32.8B parameters. The longest trained context is 986K tokens.
About YOYO-AI on Hugging Face
YOYO-AI has published 60 GGUF models that ggufmodels.com tracks, across families such as Qwen, Yoyo and Distill. The most downloaded are ZYH LLM Qwen2.5 14B, ZYH LLM Qwen2.5 14B V2 and Qwen2.5 14B YOYO 1010.
The quants YOYO-AI publishes most often are Q8_0 (39), Q4_K_M (24), F16 (4) and Q6_K (3). Their Q4_K_M files range from 9.0 to 19.8 GB. Parameter counts run from 4.02B to 32.8B, and the longest trained context window is 986K tokens.
Frequently asked questions
What GGUF models has YOYO-AI published?
60 models are listed here, mainly from the Qwen, Yoyo and Distill families. The most downloaded is ZYH LLM Qwen2.5 14B.
Which quants does YOYO-AI publish?
The most common are Q8_0 (39 models), Q4_K_M (24 models), F16 (4 models) and Q6_K (3 models).