Loading…
Loading…
Models / Nemotron-H
3 models (4B to 56B) · ↓ 81.9K downloads a month · from $0.16/h on RTX 4060 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 |
|---|---|---|---|---|
| Originalnvidia/Nemotron-H-4B-Base-8K | vLLM | 9.0 GB | 13.7 GB | $0.16/h RTX 4060 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalnvidia/Nemotron-H-8B-Base-8K | vLLM | 16 GB | 22.2 GB | $0.24/h RTX 3090 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalnvidia/Nemotron-H-56B-Base-8K | vLLM | 113 GB | 131.8 GB | $1.16/h 2x Nvidia A100 |
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").