Wan2.1 models
11 Wan2.1 models on Hugging Face, from 1.4B to 17.3B parameters. At the precision each one is published in, the smallest needs about 3.2 GB of VRAM (TurboWan2.1-T2V-1.3B-Diffusers, cheapest live fit: RTX 5060 Ti) and the largest about 77.5 GB (Wan2.1-VACE-14B, cheapest live fit: A100). The cheapest way to run TurboWan2.1-T2V-1.3B-Diffusers is $0.110/hr.
Wan2.1 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Wan2.1-T2V-1.3B | 1.4B | F32 | 6.3 GB | V100 | $0.088/hr |
| Wan2.1-T2V-1.3B-Diffusers | 1.4B | F32 | 6.3 GB | V100 | $0.088/hr |
| TurboWan2.1-T2V-1.3B-Diffusers | 1.4B | BF16 | 3.2 GB | RTX 5060 Ti | $0.110/hr |
| Wan2.1-VACE-1.3B-diffusers | 2.2B | F32 | 9.6 GB | V100 | $0.088/hr |
| Wan2.1-T2V-14B | 14.3B | F32 | 63.9 GB | A100 | $1.21/hr |
| Wan2.1-T2V-14B-Diffusers | 14.3B | F32 | 63.9 GB | A100 | $1.21/hr |
| Wan2.1-I2V-14B-480P | 16.4B | F32 | 73.3 GB | A100 | $1.21/hr |
| Wan2.1-I2V-14B-720P | 16.4B | F32 | 73.3 GB | A100 | $1.21/hr |
| Wan2.1-I2V-14B-480P-Diffusers | 16.4B | F32 | 73.3 GB | A100 | $1.21/hr |
| Wan2.1-I2V-14B-720P-Diffusers | 16.4B | F32 | 73.3 GB | A100 | $1.21/hr |
| Wan2.1-VACE-14B | 17.3B | F32 | 77.5 GB | A100 | $1.21/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from Wan-AI
- Wan2.2 (7 models)
