3-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- Qwen/Qwen-Image-2512 (finetune)
- Vendor
- Qwen
- Task
- Text to image
- Quantisation
- 3-bit
- Licence
- apache-2.0
- Downloads
- 566 in the last 30 days · 1.9K all time · 3 likes
- Published
- 2026-01-01 · updated 2026-01-01 (10mo ago)
- Tags
- mflux, qwen, image-generation, apple-silicon, diffusion
Other MLX builds of Qwen/Qwen-Image-2512
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen-Image-2512-4bit | 4-bit | — | — | 16K |
| Qwen-Image-2512-6bit | 6-bit | — | — | 1.2K |
| Qwen-Image-2512-3bit (this one) | 3-bit | — | — | 566 |
| Qwen-Image-2512-5bit | 5-bit | — | — | 386 |