Downloads · 30 days
166
20% of all-time downloads
MiniMax-H3-Ref2VA-MLX-Serve-8bit
gabrielrocco/MiniMax-H3-Ref2VA-MLX-Serve-8bit
MiniMax-H3-Ref2VA-MLX-Serve-8bit is a image-to-video model from gabrielrocco. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as other.
Native Apple-Silicon package for MiniMax-H3's omni-reference Ref2VA mode. It accepts ordered image, video and audio references for character, object, scene, motion, voice and style consistency, and jointly generates v…
All-time downloads
844
Public
Repo size
69.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors69.7 GB · 100%
At a glance
- Task
- Image-to-Video
- Library
- mlx
- License
- other
- Model type
- minimax_h3
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026
- SHA
- cd20e4ec
Base models
Model card
From the Hugging Face model README
MiniMax-H3 Ref2VA — MLX Q8
Native Apple-Silicon package for MiniMax-H3's omni-reference Ref2VA mode. It accepts ordered image, video and audio references for character, object, scene, motion, voice and style consistency, and jointly generates video plus stereo audio.
The DiT and Qwen language trunk use MLX affine Q8 (group size 64). The Qwen vision tower remains BF16, as do the precision-sensitive projections and both VAEs. The package is self-contained and is consumed by the Ref2VA runtime in mlx-serve.
Limits: up to 9 images, 3 videos, 3 audio clips and 12 files total. Audio cannot be the only reference. Video/audio references are 2–15 seconds each, with at most 15 seconds total per modality.
See MODIFICATIONS.md, NOTICE and LICENSE before use.
- Task
- Image-to-Video
- Library
- mlx
- Type
- minimax_h3
- License
- other
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026