GGUF models by IsValorum
61 GGUF models quantized by IsValorum on Hugging Face. Sizes run from 96M to 42.6B parameters. The longest trained context is 256K tokens.
About IsValorum on Hugging Face
IsValorum has published 61 GGUF models that ggufmodels.com tracks, across families such as Qwen, Occamy and Clover. The most downloaded are Qwen3.8 35B A3B Distill, Swift-1.5-Qwen3.8-27B-Uncensored-MTP and Sage A1.5 APEX I MiniPlus V2.1.
The quants IsValorum publishes most often are Q8_0 (9), Q4_K_M (8), Q4_0 (6) and Q6_K (2). Their Q4_K_M files range from 0.2 to 1.3 GB. Parameter counts run from 96M to 42.6B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has IsValorum published?
61 models are listed here, mainly from the Qwen, Occamy and Clover families. The most downloaded is Qwen3.8 35B A3B Distill.
Which quants does IsValorum publish?
The most common are Q8_0 (9 models), Q4_K_M (8 models), Q4_0 (6 models) and Q6_K (2 models).