GGUF models by Flexan
72 GGUF models quantized by Flexan on Hugging Face. Sizes run from 11M to 8.19B parameters. The longest trained context is 256K tokens.
About Flexan on Hugging Face
Flexan has published 72 GGUF models that ggufmodels.com tracks, across families such as Qwen, Nope and Stage. The most downloaded are 1kz Bigcodemax, kshitijthakkar qwen3.5 moe 0.87B d0.8B and Blake XTM Arc T0.
The quants Flexan publishes most often are Q4_K_M (72), Q2_K (72), F16 (72) and Q8_0 (71). Their Q4_K_M files range from 0.0 to 5.0 GB. Parameter counts run from 11M to 8.19B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has Flexan published?
72 models are listed here, mainly from the Qwen, Nope and Stage families. The most downloaded is 1kz Bigcodemax.
Which quants does Flexan publish?
The most common are Q4_K_M (72 models), Q2_K (72 models), F16 (72 models) and Q8_0 (71 models).