Alibaba · 20B · Dense
Open text-to-image with strong English and Chinese typography
0 downloads
0 likes
2025-12 4K context
Use Cases
image
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 6.9 GB | low | — |
| Q3_K_M | 3 | 9.5 GB | moderate | — |
| Q4_K_M | 4 | 10.7 GB | good | — |
| Q5_K_M | 5 | 13.3 GB | good | — |
| Q6_K | 6 | 15.9 GB | excellent | — |
| Q8_0 | 8 | 21 GB | excellent | — |
| F16 | 16 | 41.5 GB | lossless | — |
GPUs that run Qwen Image 2512
Qwen Image 2512 needs about 10.7 GB of VRAM at Q4_K_M, so it runs comfortably on a GPU with 16 GB of VRAM or more (69 of the GPUs we track). Common cards, smallest first:
| VRAM | GPUs |
|---|---|
| 16 GB | RTX 5080 , RX 7800 XT , Arc A770 |
| 20 GB | RTX 4000 SFF Ada , RX 7900 XT , RTX 4000 Ada |
| 24 GB | RTX 4090 , RX 7900 XTX , RTX 3090 Ti |
| 32 GB | RTX 5090 |
About this model
Open text-to-image with strong English and Chinese typography