GGUF models by MoMonir
42 GGUF models quantized by MoMonir on Hugging Face. Sizes run from 2.51B to 14B parameters. The longest trained context is 1024K tokens.
About MoMonir on Hugging Face
MoMonir has published 42 GGUF models that ggufmodels.com tracks, across families such as Llama, Phi and Gemma. The most downloaded are translategemma 4b it, deepseek coder 6.7b chat and function calling and Phi 3 mini 128k instruct.
The quants MoMonir publishes most often are Q5_K_M (40), Q6_K (38), Q4_K_M (34) and Q8_0 (10). Their Q4_K_M files range from 1.6 to 8.6 GB. Parameter counts run from 2.51B to 14B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has MoMonir published?
42 models are listed here, mainly from the Llama, Phi and Gemma families. The most downloaded is translategemma 4b it.
Which quants does MoMonir publish?
The most common are Q5_K_M (40 models), Q6_K (38 models), Q4_K_M (34 models) and Q8_0 (10 models).