Loading…
Loading…
Models / Param2
1 model (17B) · ↓ 6.9K downloads a month · from $0.45/h on RTX PRO 5000 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 |
|---|---|---|---|---|
| Originalbharatgenai/Param2-17B-A2.4B-Thinking | vLLM | 34 GB | 40.7 GB | $0.45/h RTX PRO 5000 |
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").