BLIP models
3 BLIP models on Hugging Face, from 470M to 3.9B parameters. At the precision each one is published in, the smallest needs about 2.1 GB of VRAM (blip-image-captioning-large, cheapest live fit: V100) and the largest about 17.6 GB (blip2-flan-t5-xl, cheapest live fit: RTX A5000). The cheapest way to run blip-image-captioning-large is $0.088/hr.
BLIP models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| blip-image-captioning-large | 470M | F32 | 2.1 GB | V100 | $0.088/hr |
| blip2-opt-2.7b | 3.7B | F32 | 16.7 GB | RTX A5000 | $0.176/hr |
| blip2-flan-t5-xl | 3.9B | F32 | 17.6 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.
