Alibaba · 27B (14B active) · Mixture of Experts
Flagship open Wan 2.2 — 14B-active MoE for photoreal text-to-video Check if your GPU or Mac can run Wan 2.2 T2V A14B locally — 24.9 GB min, 44 GB recommended.
2025-074K context
Mixture of Experts
Total experts: 2
Active experts: 1
Active params: 14.0B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 24.9 GB | low | — |
| Q3_K_M | 3 | 28.4 GB | moderate | — |
| Q4_K_M | 4 | 30.1 GB | good | — |
| Q5_K_M | 5 | 33.6 GB | good | — |
| Q6_K | 6 | 37 GB | excellent | — |
| Q8_0 | 8 | 44 GB | excellent | — |
| F16 | 16 | 71.6 GB | lossless | — |
Can I run Wan 2.2 T2V A14B locally?
- Can I run Wan 2.2 T2V A14B locally?
- Wan 2.2 T2V A14B needs about 24.9 GB of memory at a minimum and 44 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 T2V A14B need?
- At Q4_K_M, Wan 2.2 T2V A14B uses about 30.1 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.