MiniMax · First MLX build 23 Oct 2026
MiniMax-M3.1-Flash
MLX
TextVision minimax-community
A 427B parameter vision and text model from MiniMax, with 5 MLX builds, from 3-bit to 4-bit.
- Parameters
- 427B From Hugging Face
- Quantisation
- 3-bit MiniMax-M3.1-Flash-Text-3bit
- Memory needed
- 211 GB Estimate, unified memory
- Download
- 186 GB Weights, estimated
- Downloads
- 2.9K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 211 GB at 3-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/MiniMax-M3.1-Flash-Text-3bit --prompt "Hello"MLX builds
5 on mlx-community| MiniMax-M3.1-Flash-Text-3bit | 3-bit | 186 GB | 211 GB | 2.9K |
|---|---|---|---|---|
| MiniMax-M3.1-Flash-oQ3e-mtp | 3-bit | 188 GB | 213 GB | 1.0K |
| MiniMax-M3.1-Flash-oQ3.5e-mtp | 3-bit | 188 GB | 213 GB | 707 |
| MiniMax-M3.1-Flash-oQ4e-mtp | 4-bit | 241 GB | 272 GB | 1.2K |
| MiniMax-M3.1-Flash-Text-4bit | 4-bit | 243 GB | 275 GB | 1.4K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.