GGUF models by hellork
39 GGUF models quantized by hellork on Hugging Face. Sizes run from 1.71B to 11.7B parameters. The longest trained context is 1024K tokens.
About hellork on Hugging Face
hellork has published 39 GGUF models that ggufmodels.com tracks, across families such as Qwen, Phi and InternLM. The most downloaded are Qwen3.6 12B IQ Ultra Heretic Uncensored Thinking V2 Hightop, BlenderLLM and Qwen3.6 12B IQ Ultra Heretic Uncensored Thinking V2 Hightop.
The quants hellork publishes most often are IQ4_NL (22), IQ3_XXS (5), Q4_K_M (4) and Q8_0 (2). Their Q4_K_M files range from 2.3 to 7.3 GB. Parameter counts run from 1.71B to 11.7B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has hellork published?
39 models are listed here, mainly from the Qwen, Phi and InternLM families. The most downloaded is Qwen3.6 12B IQ Ultra Heretic Uncensored Thinking V2 Hightop.
Which quants does hellork publish?
The most common are IQ4_NL (22 models), IQ3_XXS (5 models), Q4_K_M (4 models) and Q8_0 (2 models).