GGUF models by NeverSleep
40 GGUF models quantized by NeverSleep on Hugging Face. Sizes run from 7.24B to 125B parameters. The longest trained context is 1000K tokens.
About NeverSleep on Hugging Face
NeverSleep has published 40 GGUF models that ggufmodels.com tracks, across families such as Noromaid, Mistral and Miqumaid. The most downloaded are Lumimaid v0.2 12B, Lumimaid v0.2 8B and Noromaid-v0.1-mixtral-8x7b.
The quants NeverSleep publishes most often are Q5_K_M (35), Q8_0 (29), Q4_K_M (28) and Q6_K (27). Their Q4_K_M files range from 4.4 to 42.5 GB. Parameter counts run from 7.24B to 125B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has NeverSleep published?
40 models are listed here, mainly from the Noromaid, Mistral and Miqumaid families. The most downloaded is Lumimaid v0.2 12B.
Which quants does NeverSleep publish?
The most common are Q5_K_M (35 models), Q8_0 (29 models), Q4_K_M (28 models) and Q6_K (27 models).