Loading…
Loading…
Models / pplx-embed-context-v1
GPU memory needed (smallest version of each): pplx-embed-context-v1 0.6B about 1.6 GB, pplx-embed-context-v1 4B about 25.2 GB. The cheapest runs on GTX 1650 from $0.06/h right now.
2 models (0.6B to 4B) · ↓ 16K downloads a month · from $0.06/h on GTX 1650 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalperplexity-ai/pplx-embed-context-v1-0.6b | ONNX Runtime | 400 MB | 1.6 GB | $0.06/h GTX 1650 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalperplexity-ai/pplx-embed-context-v1-4b | ONNX Runtime | 16 GB | 25.2 GB | $0.16/h Nvidia V100 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").