GGUF models by WesPro
44 GGUF models quantized by WesPro on Hugging Face. Sizes run from 7.24B to 32.8B parameters. The longest trained context is 128K tokens.
About WesPro on Hugging Face
WesPro has published 44 GGUF models that ggufmodels.com tracks, across families such as Mistral, Qwen and Mullein. The most downloaded are NeuralKuno 7B slerp, Broken Tutu 24B and MS 24B Mullein v1 test c Q6 K.
The quants WesPro publishes most often are Q6_K (36), Q4_K_M (6) and Q5_K_M (3). Their Q4_K_M files range from 7.8 to 19.9 GB. Parameter counts run from 7.24B to 32.8B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has WesPro published?
44 models are listed here, mainly from the Mistral, Qwen and Mullein families. The most downloaded is NeuralKuno 7B slerp.
Which quants does WesPro publish?
The most common are Q6_K (36 models), Q4_K_M (6 models) and Q5_K_M (3 models).