Loading…
Loading…
Models / Aryabhata-1.0
GPU memory needed (smallest version of each): Aryabhata-1.0 ~7.62B about 19.5 GB. The cheapest runs on RTX 2080 Ti from $0.15/h right now.
1 model (~7.62B) · ↓ 50 downloads a month · from $0.15/h on RTX 2080 Ti 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 |
|---|---|---|---|---|
| OriginalPhysicsWallahAI/Aryabhata-1.0 | vLLM | 15 GB | 19.7 GB | $0.20/h RTX 3090 |
| Main (Prince-1)Prince-1/Aryabhata-1.0 | ONNX Runtime GenAI | 15 GB | 19.5 GB | $0.15/h RTX 2080 Ti |
| Main (onnx-community)onnx-community/Aryabhata-1.0 | ONNX Runtime GenAI | 15 GB | 19.5 GB | $0.15/h RTX 2080 Ti |
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").