mixedbread-ai models
2 mixedbread-ai models on Hugging Face, from 494M to 1.5B parameters. At the precision each one is published in, the smallest needs about 1.1 GB of VRAM (mxbai-rerank-base-v2, cheapest live fit: V100) and the largest about 3.5 GB (mxbai-rerank-large-v2, cheapest live fit: V100). The cheapest way to run mxbai-rerank-base-v2 is $0.088/hr.
mixedbread-ai models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| mxbai-rerank-base-v2 | 494M | F16 | 1.1 GB | V100 | $0.088/hr |
| mxbai-rerank-large-v2 | 1.5B | F16 | 3.5 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.
