PaliGemma models
3 PaliGemma models on Hugging Face, from 2.9B to 2.9B parameters. At the precision each one is published in, the smallest needs about 13.1 GB of VRAM (paligemma-3b-mix-224, cheapest live fit: V100) and the largest about 13.1 GB (paligemma-3b-ft-cococap-448, cheapest live fit: V100). The cheapest way to run paligemma-3b-mix-224 is $0.088/hr.
PaliGemma models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| paligemma-3b-mix-224 | 2.9B | F32 | 13.1 GB | V100 | $0.088/hr |
| paligemma-3b-pt-224 | 2.9B | F32 | 13.1 GB | V100 | $0.088/hr |
| paligemma-3b-ft-cococap-448 | 2.9B | F32 | 13.1 GB | V100 | $0.088/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.
