Alibaba · 5B · Dense
Unified text/image-to-video — the local sweet spot under Apache 2.0 Check if your GPU or Mac can run Wan 2.2 TI2V 5B locally — 20.2 GB min, 23.7 GB recommended.
2025-074K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 20.2 GB | low | — |
| Q3_K_M | 3 | 20.8 GB | moderate | — |
| Q4_K_M | 4 | 21.2 GB | good | — |
| Q5_K_M | 5 | 21.8 GB | good | — |
| Q6_K | 6 | 22.4 GB | excellent | — |
| Q8_0 | 8 | 23.7 GB | excellent | — |
| F16 | 16 | 28.8 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 20.2 GB of memory at a minimum and 23.7 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 21.2 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.