GGUF models by C10X
51 GGUF models quantized by C10X on Hugging Face. Sizes run from 9M to 30.5B parameters. The longest trained context is 256K tokens.
About C10X on Hugging Face
C10X has published 51 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and Nanbeige. The most downloaded are Qwen2.5 1.5B Claude GGUF, Gemma 3 finetuneSSD and DeepSeek R1 Distill Llama 8B.
The quants C10X publishes most often are Q8_0 (32), Q4_K_M (18), F16 (4) and Q4_0 (1). Their Q4_K_M files range from 0.3 to 18.6 GB. Parameter counts run from 9M to 30.5B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has C10X published?
51 models are listed here, mainly from the Qwen, Gemma and Nanbeige families. The most downloaded is Qwen2.5 1.5B Claude GGUF.
Which quants does C10X publish?
The most common are Q8_0 (32 models), Q4_K_M (18 models), F16 (4 models) and Q4_0 (1 models).