GGUF models by Mungert
440 GGUF models quantized by Mungert on Hugging Face. Sizes run from 23M to 360B parameters. The longest trained context is 4192K tokens.
About Mungert on Hugging Face
Mungert has published 440 GGUF models that ggufmodels.com tracks, across families such as Qwen, Granite and Llama. The most downloaded are UI-TARS-1.5-7B, Qwen2.5-VL-3B-Instruct and Hunyuan-MT-7B.
The quants Mungert publishes most often are BF16 (437), F16 (436), Q4_1 (435) and Q4_0 (435). Their Q4_K_M files range from 0.0 to 219.4 GB. Parameter counts run from 23M to 360B, and the longest trained context window is 4192K tokens.
Frequently asked questions
What GGUF models has Mungert published?
440 models are listed here, mainly from the Qwen, Granite and Llama families. The most downloaded is UI-TARS-1.5-7B.
Which quants does Mungert publish?
The most common are BF16 (437 models), F16 (436 models), Q4_1 (435 models) and Q4_0 (435 models).