MiniMax-M2.7 (4-bit)
Language model from MiniMax for agent workflows, coding and productivity tasks.
Sourced directly from the model's publisher on huggingface.co. Please double-check links and verify before downloading.
- source https://huggingface.co/mlx-community/MiniMax-M2.7-4bit
- license modified-mit
- base MiniMax-M2.7
- published 2026-10-09 by MLX Community staff
> about this model
MiniMax-M2.7 from MiniMax, converted to MLX at 4-bit by mlx-community with router layers at 8-bit. A mixture-of-experts language model for agent workflows, coding and productivity tasks. Text only.
> before you run it
Where did these weights come from?
The source link at the top of this page. Every catalog entry is published by a site admin and must carry a resolvable origin. There is no user upload path anywhere on this site.
Can I verify what I downloaded?
No checksum is published for this entry yet. Verify against the source repo's own file hashes before running it.
Will it fit in my memory?
Budget roughly 157 GB of unified memory. Context length and batch size push that up.
Is this hosted here?
No. We catalog and link; the bytes come from the origin repo. That keeps the chain of custody with whoever actually published the weights.