GGUF models by saidutta69
81 GGUF models quantized by saidutta69 on Hugging Face. Sizes run from 135M to 14.8B parameters. The longest trained context is 986K tokens.
About saidutta69 on Hugging Face
saidutta69 has published 81 GGUF models that ggufmodels.com tracks, across families such as Qwen, Lfm and MiniCPM. The most downloaded are MiniCPM V 4.7 1B heretic, lfm2.5 2.6b fable5 coding agent heretic and Qwen3 8B Heretic.
The quants saidutta69 publishes most often are Q8_0 (79), Q5_K_M (79), Q4_K_M (79) and Q6_K (78). Their Q4_K_M files range from 0.1 to 9.0 GB. Parameter counts run from 135M to 14.8B, and the longest trained context window is 986K tokens.
Frequently asked questions
What GGUF models has saidutta69 published?
81 models are listed here, mainly from the Qwen, Lfm and MiniCPM families. The most downloaded is MiniCPM V 4.7 1B heretic.
Which quants does saidutta69 publish?
The most common are Q8_0 (79 models), Q5_K_M (79 models), Q4_K_M (79 models) and Q6_K (78 models).