Alibaba · 20B · 密集（Dense）
Open text-to-image with strong English and Chinese typography 看看你的 GPU 或 Mac 跑不跑得動 Qwen Image 2512——最低 11.2 GB，建議 18.6 GB。
2025-124K context
| 量化 | 位元 | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| 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 | — |
Can I run Qwen Image 2512 locally?
- Can I run Qwen Image 2512 locally?
- Qwen Image 2512 needs about 11.2 GB of memory at a minimum and 18.6 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Qwen Image 2512 need?
- At Q4_K_M, Qwen Image 2512 uses about 10.7 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.