Qwen-Image-2.1
Alibaba Qwen's Qwen-Image-2.1 — a 7B single-stream diffusion transformer (32 layers) behind a Qwen3-VL-8B text encoder and a new 64-channel RGBA autoencoder, released 2026-09-20. One checkpoint covers text-to-image and instruction-based editing with up to ten reference images, renders natively at 2K (2048×2048) and can output a real alpha channel. It is far smaller than the 20B Qwen-Image it follows: the transformer is 13.25 GiB in bf16 and 6.76 GiB in Comfy-Org's int8 repack, so on consumer cards the text encoder (16.33 GiB bf16, 8.71 GiB int8, 5.88 GiB w4a8) is the larger file. The licence changed with the size: the Qwen Research License Agreement permits non-commercial use only, where Qwen-Image was Apache-2.0. Native in ComfyUI from v0.37.0.
Other models grouped with Qwen-Image-2.1. Sizes and modalities can differ, and nothing here says whether one fits your GPU — open a model for its own compatibility table.
| GPU | VRAM | Series | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|---|---|
| RTX 5060 Ti | 16GB | 50 | 21.39s | ✓ | 2benchesrecipe | check ↗ | |
| 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 3060 Ti | 8GB | 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 | 8GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4060 Ti 16GB | 16GB | 40 | ~ | recipe | check ↗ | ||
| RTX 4060 Ti 8GB | 8GB | 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 | 8GB | 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 7900 XTX | 24GB | amd | ~ | recipe | check ↗ |
- VRAM
- 16GB
- Best speed
- 21.39s
- Min VRAM
- Evidence
- 2benches
- 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
- 8GB
- Best speed
- Min VRAM
- VRAM
- 12GB
- Best speed
- Min VRAM
- VRAM
- 24GB
- Best speed
- Min VRAM
- VRAM
- 24GB
- Best speed
- Min VRAM
- VRAM
- 8GB
- Best speed
- Min VRAM
- VRAM
- 16GB
- Best speed
- Min VRAM
- VRAM
- 8GB
- 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
- 8GB
- 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
- 24GB
- Best speed
- Min VRAM
✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit