GGUF models by AtomicChat
102 GGUF models quantized by AtomicChat on Hugging Face. Sizes run from 2M to 2780B parameters. The longest trained context is 1024K tokens.
About AtomicChat on Hugging Face
AtomicChat has published 102 GGUF models that ggufmodels.com tracks, across families such as Qwen, Ling and Gemma. The most downloaded are Qwen Image 2.1 Turbo Uncensored, Qwen3.8 Flash Next and Ling 3.0 Flash.
The quants AtomicChat publishes most often are Q8_0 (72), Q6_K (59), Q4_K_M (54) and Q5_K_M (52). Their Q4_K_M files range from 0.1 to 354.4 GB. Parameter counts run from 2M to 2780B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has AtomicChat published?
102 models are listed here, mainly from the Qwen, Ling and Gemma families. The most downloaded is Qwen Image 2.1 Turbo Uncensored.
Which quants does AtomicChat publish?
The most common are Q8_0 (72 models), Q6_K (59 models), Q4_K_M (54 models) and Q5_K_M (52 models).