olmOCR models
2 olmOCR models on Hugging Face, from 8.3B to 8.3B parameters. At the precision each one is published in, the smallest needs about 9.3 GB of VRAM (olmOCR-2-7B-1025-FP8, cheapest live fit: RTX 4070 Super) and the largest about 18.5 GB (olmOCR-2-7B-1025, cheapest live fit: RTX A5000). The cheapest way to run olmOCR-2-7B-1025-FP8 is $0.121/hr.
olmOCR models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| olmOCR-2-7B-1025 | 8.3B | BF16 | 18.5 GB | RTX A5000 | $0.176/hr |
| olmOCR-2-7B-1025-FP8 | 8.3B | F8_E4M3 | 9.3 GB | RTX 4070 Super | $0.121/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.
