Model Card: MiniMax-H3 GGUFs

Directory Structure

πŸ“‚ ComfyUI/
β”œβ”€β”€ πŸ“‚ models/
β”‚   β”œβ”€β”€ πŸ“‚ unet/
β”‚   β”‚   β”œβ”€β”€ MiniMax-H3-FL2VA-<Q_>.gguf
β”‚   β”œβ”€β”€ πŸ“‚ text_encoders/
β”‚   β”‚   β”œβ”€β”€ qwen3vl_32b_minimax_h3_Q4_K_M.gguf
β”‚   β”œβ”€β”€ πŸ“‚ vae/
β”‚   β”‚   β”œβ”€β”€ minimax_h3_audio_vae_fp32.safetensors
β”‚   β”‚   └── minimax_h3_video_vae_fp16.safetensors

vaes can be found here, you need both: https://huggingface.co/Comfy-Org/MiniMax-H3/tree/main/vae

Licensing and Permissions

i have permission under a license agreement with MiniMax as shown in the email below. (i blurred out my real name for privacy reasons, but it clearly shows Rebel AI as approved) Screenshot (198)

Downloads last month
-
GGUF
Model size
33B params
Architecture
wan
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for realrebelai/MiniMax-H3_GGUFs

Quantized
(3)
this model