Nemotron-H models
3 Nemotron-H models on Hugging Face, from 8.1B to 56.3B parameters. At the precision each one is published in, the smallest needs about 18.1 GB of VRAM (Nemotron-H-8B-Base-8K, cheapest live fit: RTX A5000) and the largest about 126 GB (Nemotron-H-56B-Base-8K, cheapest live fit: RTX 5060 Ti). The cheapest way to run Nemotron-H-8B-Base-8K is $0.176/hr.
Nemotron-H models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Nemotron-H-8B-Base-8K | 8.1B | BF16 | 18.1 GB | RTX A5000 | $0.176/hr |
| Nemotron-H-8B-Reasoning-128K | 8.1B | BF16 | 18.1 GB | RTX A5000 | $0.176/hr |
| Nemotron-H-56B-Base-8K | 56.3B | BF16 | 126 GB | RTX 5060 Ti × 8 | $0.880/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from NVIDIA
- Parakeet (7 models)
- Nemotron 3 (16 models)
- Cosmos (6 models)
- Nemotron Nano (4 models)
- Nemotron (5 models)
- Nemotron Labs (4 models)
