stepfun-ai models
4 stepfun-ai models on Hugging Face, from 561M to 321.0B parameters. At the precision each one is published in, the smallest needs about 1.3 GB of VRAM (GOT-OCR-2.0-hf, cheapest live fit: RTX 5060 Ti) and the largest about 717 GB (step3, cheapest live fit: RTX PRO 6000). The cheapest way to run GOT-OCR-2.0-hf is $0.110/hr.
stepfun-ai models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| GOT-OCR-2.0-hf | 561M | BF16 | 1.3 GB | RTX 5060 Ti | $0.110/hr |
| GOT-OCR2_0 | 716M | BF16 | 1.6 GB | RTX 5060 Ti | $0.110/hr |
| Step-3.5-Flash | 199.4B | BF16 | 446 GB | RTX PRO 6000 × 5 | $6.88/hr |
| step3 | 321.0B | BF16 | 717 GB | RTX PRO 6000 × 8 | $11.00/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.
