MiniMax H3

Repackaged model files for ComfyUI.

Original model repository:

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
│   ├── 📂 loras/
│   │   ├── minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensors
│   │   ├── minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors
│   │   └── minimax_h3_ref2v_turbo_4step_v0.1_comfyui_bf16.safetensors
│   ├── 📂 vae/
│   │   ├── minimax_h3_audio_vae_fp32.safetensors
│   │   └── minimax_h3_video_vae_fp16.safetensors

Workflows

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for KENIC-1/Comfy-Org-MiniMax-H3-loras

Base model

MiniMaxAI/MiniMax-H3

Finetuned

(61)

this model