4-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-2.1 (finetune)
- Vendor
- Qwen
- Task
- Text to image
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 11K in the last 30 days · 36K all time · 2 likes
- Published
- 2026-09-26 · updated 2026-09-26 (1mo ago)
- Tags
- mflux, image-to-image, qwen-image
Other MLX builds of Qwen/Qwen-Image-2.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen-Image-2.1-mflux-q4 (this one) | 4-bit | — | — | 11K |
| Qwen-Image-2.1-MLX-4bit | 4-bit | — | — | 0 |