Alibaba Qwen · First MLX build 1 Jan 2026
Qwen-Image-2512
MLX
Image apache-2.0
A text to image model from Alibaba Qwen, with 4 MLX builds, from 4-bit to 5-bit.
- Parameters
- — Not published
- Quantisation
- 4-bit Qwen-Image-2512-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 17K This build, last 30 days
- Task
- Text to image Image
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Qwen-Image-2512-4bitMLX builds
4 on mlx-community| Qwen-Image-2512-4bit | 4-bit | — | — | 17K |
|---|---|---|---|---|
| Qwen-Image-2512-6bit | 6-bit | — | — | 1.2K |
| Qwen-Image-2512-3bit | 3-bit | — | — | 559 |
| Qwen-Image-2512-5bit | 5-bit | — | — | 382 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.