GGUF models by unsloth
391 GGUF models quantized by unsloth on Hugging Face. Sizes run from 33M to 2780B parameters. The longest trained context is 10240K tokens.
About unsloth on Hugging Face
unsloth has published 391 GGUF models that ggufmodels.com tracks, across families such as Qwen, Gemma and DeepSeek. The most downloaded are Qwen3.8-27B, MiniMax H3 and Qwen Image 2.1.
The quants unsloth publishes most often are Q8_0 (358), Q4_K_M (357), Q3_K_M (351) and Q5_K_M (350). Their Q4_K_M files range from 0.1 to 629.6 GB. Parameter counts run from 33M to 2780B, and the longest trained context window is 10240K tokens.
Frequently asked questions
What GGUF models has unsloth published?
391 models are listed here, mainly from the Qwen, Gemma and DeepSeek families. The most downloaded is Qwen3.8-27B.
Which quants does unsloth publish?
The most common are Q8_0 (358 models), Q4_K_M (357 models), Q3_K_M (351 models) and Q5_K_M (350 models).