Loading…
Loading…
Models / deberta-v3-base-injection
GPU memory needed (smallest version of each): deberta-v3-base-injection ~184M about 2.1 GB. The cheapest runs on GTX 1650 from $0.06/h right now.
1 model (~184M) · ↓ 3.9K 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 |
|---|---|---|---|---|
| onnx (protectai)protectai/deberta-v3-base-injection-onnx | ONNX Runtime | 740 MB | 2.1 GB | $0.06/h GTX 1650 |
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").