ai-models/MiniMax-H3
2
0
Fork 0
mirror of https://www.modelscope.cn/Comfy-Org/MiniMax-H3.git synced 2026-08-30 22:32:57 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
bfc8546940b6bdd7ba87f57b3e6e7f021d9b4d90
MiniMax-H3/README.md
systemd bfc8546940 Update README.md (batch 1/1)
2026-08-15 12:06:35 +00:00

2.1 KiB
Raw Blame History

license, license_name, license_link, tags, base_model
license license_name license_link tags base_model
other minimax-h3-community-license-agreement https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE
comfyui
diffusion-single-file
MiniMaxAI/MiniMax-H3

MiniMax H3

Repackaged model files for ComfyUI.

Original model repository: https://huggingface.co/MiniMaxAI/MiniMax-H3

The Qwen3-VL-32B nvfp4_awq quant is converted from: https://huggingface.co/cybermotaz/Qwen3-VL-32B-Instruct-NVFP4

This nvfp4 text encoder does not require Blackwell GPU to use.

For diffusion models prefer int8_convrot if you are able to use pytorch with cu130.

fp8_scaled should only be used if you cannot use int8_convrot.

Place the files in the following folders:

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   ├── minimax_h3_fl2va_bf16.safetensors
│   │   ├── minimax_h3_fl2va_int8_convrot.safetensors
│   │   ├── minimax_h3_fl2va_pruned_bf16.safetensors
│   │   ├── minimax_h3_fl2va_pruned_int8_convrot.safetensors
│   │   ├── minimax_h3_fl2va_pruned_fp8_scaled.safetensors
│   │   ├── minimax_h3_ref2va_bf16.safetensors
│   │   ├── minimax_h3_ref2va_int8_convrot.safetensors
│   │   ├── minimax_h3_ref2va_pruned_bf16.safetensors
│   │   ├── minimax_h3_ref2va_pruned_int8_convrot.safetensors
│   │   └── minimax_h3_ref2va_pruned_fp8_scaled.safetensors
│   ├── 📂 text_encoders/
│   │   ├── qwen3vl_32b_minimax_h3_bf16.safetensors
│   │   ├── qwen3vl_32b_minimax_h3_int8_convrot.safetensors
│   │   └── qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
│   ├── 📂 vae/
│   │   ├── minimax_h3_audio_vae_fp32.safetensors
│   │   └── minimax_h3_video_vae_fp16.safetensors

Workflows