§01·model · /models
Qwen-Image
imageactiveApache-2.0
Alibaba Qwen's Qwen-Image — a 20B MMDiT image foundation model notable for complex text rendering, Chinese especially, and precise image editing. Apache-2.0. Twenty-two cards here carry a recipe with a 12 GB floor, which for a 20B image model means quantised weights rather than the native path. Text rendering is the reason to reach for it over a smaller model: it is the capability that degrades first elsewhere.
§02·same family
1 other modelOther models grouped with Qwen-Image. Sizes and modalities can differ, and nothing here says whether one fits your GPU — open a model for its own compatibility table.
§03·GPUs that run this model
22 total| GPU | VRAM | Series | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|---|---|
| Apple M2 Max | 64GB | apple | ~ | recipe | check ↗ | ||
| Apple M3 Max | 48GB | apple | ~ | recipe | check ↗ | ||
| Apple M4 Max | 48GB | apple | ~ | recipe | check ↗ | ||
| RTX 3060 | 12GB | 30 | ~ | recipe | check ↗ | ||
| RTX 3080 Ti | 12GB | 30 | ~ | recipe | check ↗ | ||
| RTX 3090 | 24GB | 30 | ~ | recipe | check ↗ | ||
| RTX 3090 Ti | 24GB | 30 | ~ | recipe | check ↗ | ||
| RTX 4060 Ti 16GB | 16GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4070 | 12GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4070 Super | 12GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4070 Ti | 12GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4070 Ti Super | 16GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4080 | 16GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4080 Super | 16GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4090 | 24GB | 40 | ~ | recipe | check ↗ | ||
| RTX 5060 Ti | 16GB | 50 | ~ | recipe | check ↗ | ||
| RTX 5070 | 12GB | 50 | ~ | recipe | check ↗ | ||
| RTX 5070 Ti | 16GB | 50 | ~ | recipe | check ↗ | ||
| RTX 5080 | 16GB | 50 | ~ | recipe | check ↗ | ||
| RTX 5090 | 32GB | 50 | ~ | recipe | check ↗ | ||
| RX 7800 XT | 16GB | amd | ~ | recipe | check ↗ | ||
| RX 7900 XTX | 24GB | amd | ~ | recipe | check ↗ |
- VRAM
- 64GB
- Best speed
- Min VRAM
- VRAM
- 48GB
- Best speed
- Min VRAM
- VRAM
- 48GB
- Best speed
- Min VRAM
- VRAM
- 12GB
- Best speed
- Min VRAM
- VRAM
- 12GB
- Best speed
- Min VRAM
- VRAM
- 24GB
- Best speed
- Min VRAM
- VRAM
- 24GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 12GB
- Best speed
- Min VRAM
- VRAM
- 12GB
- Best speed
- Min VRAM
- VRAM
- 12GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 24GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 12GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 32GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 24GB
- Best speed
- Min VRAM
✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit