perplexity-ai models
2 perplexity-ai models on Hugging Face, from 596M to 8.4B parameters. At the precision each one is published in, the smallest needs about 1.3 GB of VRAM (pplx-pii-masking, cheapest live fit: RTX 3060) and the largest about 37.6 GB (pplx-embed-v2-context-9b-preview, cheapest live fit: RTX A6000). The cheapest way to run pplx-pii-masking is $0.110/hr.
perplexity-ai models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| pplx-pii-masking | 596M | BF16 | 1.3 GB | RTX 3060 | $0.110/hr |
| pplx-embed-v2-context-9b-preview | 8.4B | F32 | 37.6 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.
