Alibaba · 1.3B · 密集（Dense）
Tiny open text-to-video — 480p clips on 8GB consumer GPUs 看看你的 GPU 或 Mac 跑不跑得動 Wan 2.1 T2V 1.3B——最低 1 GB，建議 2 GB。
2025-024K context
| 量化 | 位元 | VRAM | 品質 | 狀態 |
|---|---|---|---|---|
| Q2_K | 2 | 0.9 GB | low | — |
| Q3_K_M | 3 | 1.1 GB | moderate | — |
| Q4_K_M | 4 | 1.2 GB | good | — |
| Q5_K_M | 5 | 1.3 GB | good | — |
| Q6_K | 6 | 1.5 GB | excellent | — |
| Q8_0 | 8 | 1.8 GB | excellent | — |
| F16 | 16 | 3.2 GB | lossless | — |
Can I run Wan 2.1 T2V 1.3B locally?
- Can I run Wan 2.1 T2V 1.3B locally?
- Wan 2.1 T2V 1.3B needs about 1 GB of memory at a minimum and 2 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 2.1 T2V 1.3B need?
- At Q4_K_M, Wan 2.1 T2V 1.3B uses about 1.2 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.