GGUF models by Tristepin
61 GGUF models quantized by Tristepin on Hugging Face. Sizes run from 44M to 12.2B parameters. The longest trained context is 1000K tokens.
About Tristepin on Hugging Face
Tristepin has published 61 GGUF models that ggufmodels.com tracks, across families such as Udk, Qwn and Uzdpqwn. The most downloaded are qwn3gzdm4b ins, qwn3gdt364b ins1 and qwn3gzdm4b ins2.
The quants Tristepin publishes most often are Q6_K (38), Q4_K_M (18), Q5_K_M (8) and Q8_0 (7). Their Q4_K_M files range from 0.8 to 7.5 GB. Parameter counts run from 44M to 12.2B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has Tristepin published?
61 models are listed here, mainly from the Udk, Qwn and Uzdpqwn families. The most downloaded is qwn3gzdm4b ins.
Which quants does Tristepin publish?
The most common are Q6_K (38 models), Q4_K_M (18 models), Q5_K_M (8 models) and Q8_0 (7 models).