MLX Community · First MLX build 14 Jan 2026
MiniMax-M2.1-REAP-40
MLX
Text apache-2.0
A 139B parameter text generation model, with 3 MLX builds, from 4-bit to 8-bit.
- Parameters
- 139B From Hugging Face
- Quantisation
- 4-bit MiniMax-M2.1-REAP-40-4bit
- Memory needed
- 90 GB Estimate, unified memory
- Download
- 78.3 GB Weights, estimated
- Downloads
- 37 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 90 GB at 4-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-M2.1-REAP-40-4bit --prompt "Hello"MLX builds
3 on mlx-community| MiniMax-M2.1-REAP-40-4bit | 4-bit | 78.3 GB | 90 GB | 37 |
|---|---|---|---|---|
| MiniMax-M2.1-REAP-40-5bit | 5-bit | 95.7 GB | 109 GB | 23 |
| MiniMax-M2.1-REAP-40-8bit | 8-bit | 148 GB | 168 GB | 18 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.