BAAI models
2 BAAI models on Hugging Face, from 2.5B to 9.2B parameters. At the precision each one is published in, the smallest needs about 11.2 GB of VRAM (bge-reranker-v2-gemma, cheapest live fit: V100) and the largest about 41.3 GB (bge-reranker-v2.5-gemma2-lightweight, cheapest live fit: RTX A6000). The cheapest way to run bge-reranker-v2-gemma is $0.088/hr.
BAAI models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| bge-reranker-v2-gemma | 2.5B | F32 | 11.2 GB | V100 | $0.088/hr |
| bge-reranker-v2.5-gemma2-lightweight | 9.2B | F32 | 41.3 GB | RTX A6000 | $0.363/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.
