Ovis models
6 Ovis models on Hugging Face, from 853M to 10.2B parameters. At the precision each one is published in, the smallest needs about 1.9 GB of VRAM (OvisOCR2, cheapest live fit: RTX 5060 Ti) and the largest about 22.8 GB (Ovis1.6-Gemma2-9B, cheapest live fit: RTX A5000). The cheapest way to run OvisOCR2 is $0.110/hr.
Ovis models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| OvisOCR2 | 853M | BF16 | 1.9 GB | RTX 5060 Ti | $0.110/hr |
| Ovis2-1B | 1.3B | BF16 | 2.8 GB | RTX 5060 Ti | $0.110/hr |
| Ovis1.6-Llama3.2-3B | 4.1B | BF16 | 9.3 GB | RTX 5060 Ti | $0.110/hr |
| Ovis2-4B | 4.6B | BF16 | 10.3 GB | RTX 5060 Ti | $0.110/hr |
| Ovis2.5-9B | 9.2B | BF16 | 20.5 GB | RTX A5000 | $0.176/hr |
| Ovis1.6-Gemma2-9B | 10.2B | BF16 | 22.8 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.
