Modelpublic

nif0/Qwen3-VL-32B-Instruct-MiniMax-H3-GGUF

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

14likes26kdownloads

Model Card

Pruned layers after 49 as they arent needed for use with MiniMax H3.

You need only the model for T2V and model + mmproj for I2V. place both the model and the mmproj file in text_encoder folder.

Can be used in ComfyUI with my fork of City96's ComfyUI-GGUF. https://github.com/Nif00/ComfyUI-GGUF