Stable Diffusion 3 models
3 Stable Diffusion 3 models on Hugging Face, from 2.1B to 8.1B parameters. At the precision each one is published in, the smallest needs about 4.7 GB of VRAM (stable-diffusion-3-medium-diffusers, cheapest live fit: V100) and the largest about 18.2 GB (stable-diffusion-3.5-large, cheapest live fit: RTX A5000). The cheapest way to run stable-diffusion-3-medium-diffusers is $0.088/hr.
Stable Diffusion 3 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| stable-diffusion-3-medium-diffusers | 2.1B | F16 | 4.7 GB | V100 | $0.088/hr |
| stable-diffusion-3.5-medium | 2.5B | BF16 | 5.5 GB | RTX 5060 Ti | $0.110/hr |
| stable-diffusion-3.5-large | 8.1B | BF16 | 18.2 GB | RTX A5000 | $0.176/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 Stability AI
- Stable Diffusion XL (33 models)
- Stable Diffusion (9 models)
- StableLM (3 models)
- stabilityai (3 models)
