FastVideo models
3 FastVideo models on Hugging Face, from 5.0B to 35.0B parameters. At the precision each one is published in, the smallest needs about 11.2 GB of VRAM (FastWan2.2-TI2V-5B-FullAttn-Diffusers, cheapest live fit: RTX 5060 Ti) and the largest about 78.3 GB (FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree, cheapest live fit: A100). The cheapest way to run FastWan2.2-TI2V-5B-FullAttn-Diffusers is $0.110/hr.
FastVideo models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| FastWan2.2-TI2V-5B-FullAttn-Diffusers | 5.0B | BF16 | 11.2 GB | RTX 5060 Ti | $0.110/hr |
| FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree | 35.0B | BF16 | 78.3 GB | A100 | $1.31/hr |
| FastVideo-Minimax-FastH3-Preview-v0.2 | 35.0B | BF16 | 78.3 GB | A100 | $1.31/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.
