GGUF models by bruhzair
358 GGUF models quantized by bruhzair on Hugging Face. Sizes run from 70.6B to 123B parameters. The longest trained context is 256K tokens.
About bruhzair on Hugging Face
bruhzair has published 358 GGUF models that ggufmodels.com tracks, across families such as Prototype, Protofuel and Proxy. The most downloaded are Alpha Model 1b 105B, prototype 0.4x144 Q6 K and prototype 0.4x216 Q6 K.
The quants bruhzair publishes most often are Q6_K (140), Q4_K (118), Q8_0 (82) and Q4_K_M (11). Their Q4_K_M files range from 63.0 to 73.2 GB. Parameter counts run from 70.6B to 123B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has bruhzair published?
358 models are listed here, mainly from the Prototype, Protofuel and Proxy families. The most downloaded is Alpha Model 1b 105B.
Which quants does bruhzair publish?
The most common are Q6_K (140 models), Q4_K (118 models), Q8_0 (82 models) and Q4_K_M (11 models).