GGUF models by NANI-Nithin
36 GGUF models quantized by NANI-Nithin on Hugging Face. Sizes run from 354M to 37.4B parameters. The longest trained context is 1024K tokens.
About NANI-Nithin on Hugging Face
NANI-Nithin has published 36 GGUF models that ggufmodels.com tracks, across families such as Lfm, Horizon and MiniCPM. The most downloaded are K2 Horizon MoVA 36B A4B, LFM2.5-24B-A2B and Muse Glimmer 30B.
The quants NANI-Nithin publishes most often are Q8_0 (34), Q6_K (34), Q4_K_M (34) and Q5_K_M (33). Their Q4_K_M files range from 0.2 to 25.4 GB. Parameter counts run from 354M to 37.4B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has NANI-Nithin published?
36 models are listed here, mainly from the Lfm, Horizon and MiniCPM families. The most downloaded is K2 Horizon MoVA 36B A4B.
Which quants does NANI-Nithin publish?
The most common are Q8_0 (34 models), Q6_K (34 models), Q4_K_M (34 models) and Q5_K_M (33 models).