Alibaba · 5B · 密集（Dense）
Unified text/image-to-video — the local sweet spot under Apache 2.0 看看你的 GPU 或 Mac 跑不跑得動 Wan 2.2 TI2V 5B——最低 2.8 GB，建議 4.7 GB。
2025-074K context
| 量化 | 位元 | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| Q2_K | 2 | 2.1 GB | low | — |
| Q3_K_M | 3 | 2.7 GB | moderate | — |
| Q4_K_M | 4 | 3.1 GB | good | — |
| Q5_K_M | 5 | 3.7 GB | good | — |
| Q6_K | 6 | 4.3 GB | excellent | — |
| Q8_0 | 8 | 5.6 GB | excellent | — |
| F16 | 16 | 10.7 GB | lossless | — |
Can I run Wan 2.2 TI2V 5B locally?
- Can I run Wan 2.2 TI2V 5B locally?
- Wan 2.2 TI2V 5B needs about 2.8 GB of memory at a minimum and 4.7 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 Wan 2.2 TI2V 5B need?
- At Q4_K_M, Wan 2.2 TI2V 5B uses about 3.1 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.