4-bit Open on Hugging Face
Parameters
427B
Weights (est.)
≈ 241 GB
Mac memory (est.)
512 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/MiniMax-M3-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- MiniMaxAI/MiniMax-M3 (quantized)
- Vendor
- MiniMaxAI
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- minimax-community
- Downloads
- 554 in the last 30 days · 12K all time · 7 likes
- Published
- 2026-06-13 · updated 2026-06-20 (4mo ago)
- Tags
- minimax_m3_vl, multimodal, agent, coding, video, custom_code