GGUF models by Chungulus
34 GGUF models quantized by Chungulus on Hugging Face. Sizes run from 4.21B to 64.8B parameters. The longest trained context is 2048K tokens.
About Chungulus on Hugging Face
Chungulus has published 34 GGUF models that ggufmodels.com tracks, across families such as Qwen, Agents and Arete. The most downloaded are Qwen3.8 27B Q3 K M, Qwen3.8 27B Q8 0 and Qwen3.8 27B Q6 K.
The quants Chungulus publishes most often are Q4_K_M (7), Q8_0 (6), Q6_K (6) and Q3_K_M (6). Their Q4_K_M files range from 2.7 to 38.8 GB. Parameter counts run from 4.21B to 64.8B, and the longest trained context window is 2048K tokens.
Frequently asked questions
What GGUF models has Chungulus published?
34 models are listed here, mainly from the Qwen, Agents and Arete families. The most downloaded is Qwen3.8 27B Q3 K M.
Which quants does Chungulus publish?
The most common are Q4_K_M (7 models), Q8_0 (6 models), Q6_K (6 models) and Q3_K_M (6 models).