Alibaba Qwen · First MLX build 29 Apr 2025
Qwen3-235B-A22B
MLX
Text apache-2.0
A 235B parameter text generation model from Alibaba Qwen, with 6 MLX builds, from 3-bit to 8-bit.
- Parameters
- 235B From Hugging Face
- Quantisation
- 4-bit Qwen3-235B-A22B-4bit
- Memory needed
- 150 GB Estimate, unified memory
- Download
- 132 GB Weights, estimated
- Downloads
- 4.7K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 6 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 150 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/Qwen3-235B-A22B-4bit --prompt "Hello"MLX builds
6 on mlx-community| Qwen3-235B-A22B-3bit | 3-bit | 103 GB | 117 GB | 40 |
|---|---|---|---|---|
| Qwen3-235B-A22B-3bit-DWQ | 3-bit DWQ | 103 GB | 117 GB | 40 |
| Qwen3-235B-A22B-4bit | 4-bit | 132 GB | 150 GB | 4.7K |
| Qwen3-235B-A22B-mixed-3-4bit | 4-bit | 132 GB | 150 GB | 23 |
| Qwen3-235B-A22B-mixed-3-6bit | 6-bit | 191 GB | 216 GB | 26 |
| Qwen3-235B-A22B-8bit | 8-bit | 250 GB | 282 GB | 1.3K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.