datalab-to models
3 datalab-to models on Hugging Face, from 686M to 9.7B parameters. At the precision each one is published in, the smallest needs about 1.5 GB of VRAM (surya-ocr-2, cheapest live fit: RTX 5060 Ti) and the largest about 21.6 GB (lift, cheapest live fit: RTX A5000). The cheapest way to run surya-ocr-2 is $0.110/hr.
datalab-to models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| surya-ocr-2 | 686M | BF16 | 1.5 GB | RTX 5060 Ti | $0.110/hr |
| chandra-ocr-2 | 5.3B | BF16 | 11.8 GB | RTX 5060 Ti | $0.110/hr |
| lift | 9.7B | BF16 | 21.6 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.
