Loading…
Loading…
Models / Llama-Prompt-Guard-2
GPU memory needed (smallest version of each): Llama-Prompt-Guard-2 22M about 1.1 GB, Llama-Prompt-Guard-2 86M about 1.4 GB. The cheapest runs on Quadro P4000 from $0.07/h right now.
2 models (22M to 86M) · ↓ 13.5K downloads a month · from $0.07/h on Quadro P4000 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 |
|---|---|---|---|---|
| onnx (gravitee-io)gravitee-io/Llama-Prompt-Guard-2-22M-onnx | ONNX Runtime | 70 MB | 1.1 GB | $0.07/h Quadro P4000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| onnx (gravitee-io)gravitee-io/Llama-Prompt-Guard-2-86M-onnx | ONNX Runtime | 280 MB | 1.4 GB | $0.07/h Quadro P4000 |
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").