Loading…
Loading…
Models / OpenReasoning-Nemotron
GPU memory needed (smallest version of each): OpenReasoning-Nemotron 1.5B about 5.9 GB, OpenReasoning-Nemotron 7B about 19.5 GB, OpenReasoning-Nemotron 32B about 77.4 GB. The cheapest runs on Quadro P4000 from $0.07/h right now.
3 models (1.5B to 32B) · ↓ 836 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 |
|---|---|---|---|---|
| Main (onnx-community)onnx-community/OpenReasoning-Nemotron-1.5B | ONNX Runtime GenAI | 3.6 GB | 5.9 GB | $0.07/h Quadro P4000 |
| Main (Prince-1)Prince-1/OpenReasoning-Nemotron-1.5B | ONNX Runtime GenAI | 3.6 GB | 5.9 GB | $0.07/h Quadro P4000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Main (Prince-1)Prince-1/OpenReasoning-Nemotron-7B | ONNX Runtime GenAI | 15 GB | 19.5 GB | $0.18/h Nvidia V100 |
| Main (onnx-community)onnx-community/OpenReasoning-Nemotron-7B | ONNX Runtime GenAI | 15 GB | 19.5 GB | $0.18/h Nvidia V100 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalnvidia/OpenReasoning-Nemotron-32B | vLLM | 66 GB | 77.4 GB | $0.89/h 2x Nvidia A40 |
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").