GGUF models by Manojb
345 GGUF models quantized by Manojb on Hugging Face. Sizes run from 331M to 79.7B parameters. The longest trained context is 488K tokens.
About Manojb on Hugging Face
Manojb has published 345 GGUF models that ggufmodels.com tracks, across families such as Qwen, Ling and Lfm. The most downloaded are Qwen3.5 9B Uncensored HauhauCS Aggressive Q4 K M, Qwen3 4B toolcalling gguf codex and Qwen3.5-4B.
The quants Manojb publishes most often are Q4_K_M (30), Q8_0 (27), Q6_K (22) and Q5_K_M (18). Their Q4_K_M files range from 0.5 to 21.2 GB. Parameter counts run from 331M to 79.7B, and the longest trained context window is 488K tokens.
Frequently asked questions
What GGUF models has Manojb published?
345 models are listed here, mainly from the Qwen, Ling and Lfm families. The most downloaded is Qwen3.5 9B Uncensored HauhauCS Aggressive Q4 K M.
Which quants does Manojb publish?
The most common are Q4_K_M (30 models), Q8_0 (27 models), Q6_K (22 models) and Q5_K_M (18 models).