Loading…
Loading…
Models / sarvam-1
1 model (~2.53B) · ↓ 8.9K downloads a month · from $0.09/h on RTX 3060 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 |
|---|---|---|---|---|
| Originalsarvamai/sarvam-1 | vLLM | 5.0 GB | 8.9 GB | $0.10/h RTX 3060 |
| Main (Prince-1)Prince-1/sarvam-1 | ONNX Runtime GenAI | 5.1 GB | 8.3 GB | $0.09/h RTX 3060 |
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").