BAAI · First MLX build 29 Jul 2026
AREX-Base
MLX
Text apache-2.0
A 123B parameter text generation model from BAAI, with one MLX build at MXFP4.
- Parameters
- 123B From Hugging Face
- Quantisation
- MXFP4 AREX-Base-mixed-mxfp4-bf16
- Memory needed
- 90 GB Estimate, unified memory
- Download
- 78.4 GB Weights, estimated
- Downloads
- 45 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 90 GB at MXFP4
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/AREX-Base-mixed-mxfp4-bf16 --prompt "Hello"MLX builds
1 on mlx-community| AREX-Base-mixed-mxfp4-bf16 | MXFP4 | 78.4 GB | 90 GB | 45 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.