Loading…
Loading…
Models / Nemotron-Research-Reasoning-Qwen
GPU memory needed (smallest version of each): Nemotron-Research-Reasoning-Qwen 1.5B about 6.4 GB. The cheapest runs on RTX A4000 from $0.13/h right now.
1 model (1.5B) · ↓ 1.2K downloads a month · from $0.13/h on RTX A4000 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 |
|---|---|---|---|---|
| Originalnvidia/Nemotron-Research-Reasoning-Qwen-1.5B | vLLM | 3.5 GB | 6.4 GB | $0.13/h RTX A4000 |
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").