perplexity-ai models
2 perplexity-ai models from perplexity-ai on Hugging Face, from 596M to 8.4B parameters, published by perplexity-ai in BF16 and F32, with a 256K-token context. The smallest official model, pplx-pii-masking, needs about 1.3 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Pick a size
One row per official perplexity-ai size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| pplx-pii-masking | 596M | 1.3 GB | 0.7 GB | 0.3 GB | RTX 3070 | $0.088/hr | not published for this architecture |
| pplx-embed-v2-context-9b-preview | 8.4B | 37.6 GB | 9.4 GB | 4.7 GB | RTX A6000 | $0.363/hr | not published for this architecture |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| pplx-pii-masking | 596M | BF16 | 1.3 GB | RTX 3070 | $0.088/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: the weights times a flat 1.2 overhead, with the KV cache not included. 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.