Wan2.2-T2V-5B
Wan-AI/Wan2.2-T2V-5B
Wan 2.2 5B, lightweight video generation for 24GB GPUs.
Parameters
5B
Context
32K
Downloads
210K
Likes
1.6K
Architecture
wan
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 23.9 GB RAM 35.9 · Disk 53.5 | 28.5 GB RAM 42.7 · Disk 79.5 | 36.9 GB RAM 55.4 · Disk 118.5 |
| FP88bit | 14.7 GB RAM 32.0 · Disk 46.3 | 18.8 GB RAM 32.0 · Disk 72.3 | 26.9 GB RAM 40.3 · Disk 111.3 |
| INT88bit | 14.7 GB RAM 32.0 · Disk 46.3 | 18.8 GB RAM 32.0 · Disk 72.3 | 26.9 GB RAM 40.3 · Disk 111.3 |
| AWQ4bit | 10.3 GB RAM 32.0 · Disk 42.8 | 14.2 GB RAM 32.0 · Disk 68.8 | 22.0 GB RAM 33.0 · Disk 107.8 |
| GPTQ4bit | 10.3 GB RAM 32.0 · Disk 42.8 | 14.3 GB RAM 32.0 · Disk 68.8 | 22.1 GB RAM 33.1 · Disk 107.8 |
| GGUF4bit | 10.5 GB RAM 32.0 · Disk 42.9 | 14.4 GB RAM 32.0 · Disk 68.9 | 22.2 GB RAM 33.3 · Disk 107.9 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 82.2 video-sec/GPU-h
Effective production throughput ≈ 49.3 video-sec/GPU-h
score 0.6158
1× RTX 4070S Ti
16 GB VRAM
≈ 792 video-sec/GPU-h
Effective production throughput ≈ 475.2 video-sec/GPU-h
score 0.6523
8× H100 SXM
640 GB VRAM
≈ 63.6 video-sec/GPU-h
Effective production throughput ≈ 38.2 video-sec/GPU-h
score 0.2415
1× RTX 3090
24 GB VRAM
≈ 34.7 video-sec/GPU-h
Effective production throughput ≈ 20.8 video-sec/GPU-h
score 0.6529
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 4070S Ti
16 GB VRAM
$49.5
/mo · vast
RTX 4080S
16 GB VRAM
$50.0
/mo · vast
RTX 3090
24 GB VRAM
$76.5
/mo · vast
RTX 5070 Ti
16 GB VRAM
$86.3
/mo · vast
Tesla V100
16 GB VRAM
$88.4
/mo · vast