GGUF models by Reiterate3680
37 GGUF models quantized by Reiterate3680 on Hugging Face. Sizes run from 7.62B to 70.6B parameters. The longest trained context is 1000K tokens.
About Reiterate3680 on Hugging Face
Reiterate3680 has published 37 GGUF models that ggufmodels.com tracks, across families such as Sekhmet, Starcannon and Rocinante. The most downloaded are guns and roses r1, MN 12B Lyra v1 and Nemomix v4.0 12B.
The quants Reiterate3680 publishes most often are Q4_K_L (30), Q6_K_L (28), Q6_K (16) and Q4_K_M (16). Their Q4_K_M files range from 4.9 to 15.2 GB. Parameter counts run from 7.62B to 70.6B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has Reiterate3680 published?
37 models are listed here, mainly from the Sekhmet, Starcannon and Rocinante families. The most downloaded is guns and roses r1.
Which quants does Reiterate3680 publish?
The most common are Q4_K_L (30 models), Q6_K_L (28 models), Q6_K (16 models) and Q4_K_M (16 models).