GGUF models by wop
34 GGUF models quantized by wop on Hugging Face. Sizes run from 18M to 4.21B parameters. The longest trained context is 256K tokens.
About wop on Hugging Face
wop has published 34 GGUF models that ggufmodels.com tracks, across families such as Quble, Arptron and Vordex. The most downloaded are Opus4Qwen4, Creativity lfm2 5 350M and the largest.
The quants wop publishes most often are Q8_0 (10), Q4_K_M (5), Q6_K (3) and Q5_K_M (3). Their Q4_K_M files range from 0.1 to 2.7 GB. Parameter counts run from 18M to 4.21B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has wop published?
34 models are listed here, mainly from the Quble, Arptron and Vordex families. The most downloaded is Opus4Qwen4.
Which quants does wop publish?
The most common are Q8_0 (10 models), Q4_K_M (5 models), Q6_K (3 models) and Q5_K_M (3 models).