Alibaba · 6B · Dense
8-step distilled image model — photorealism and bilingual text on 16GB cards お使いの GPU や Mac で Z-Image Turbo が動くか確認——最小 3.4 GB、推奨 5.6 GB。
2025-114K context
| 量子化 | ビット | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| Q2_K | 2 | 2.4 GB | low | — |
| Q3_K_M | 3 | 3.2 GB | moderate | — |
| Q4_K_M | 4 | 3.6 GB | good | — |
| Q5_K_M | 5 | 4.3 GB | good | — |
| Q6_K | 6 | 5.1 GB | excellent | — |
| Q8_0 | 8 | 6.6 GB | excellent | — |
| F16 | 16 | 12.8 GB | lossless | — |
Can I run Z-Image Turbo locally?
- Can I run Z-Image Turbo locally?
- Z-Image Turbo needs about 3.4 GB of memory at a minimum and 5.6 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 Z-Image Turbo need?
- At Q4_K_M, Z-Image Turbo uses about 3.6 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.