Nemotron Nano models
4 Nemotron Nano models on Hugging Face, from 8.9B to 13.2B parameters. At the precision each one is published in, the smallest needs about 9.9 GB of VRAM (NVIDIA-Nemotron-Nano-9B-v2-FP8, cheapest live fit: RTX 5060 Ti) and the largest about 27.5 GB (NVIDIA-Nemotron-Nano-12B-v2, cheapest live fit: RTX 4080 Super). The cheapest way to run NVIDIA-Nemotron-Nano-9B-v2-FP8 is $0.110/hr.
Nemotron Nano models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| NVIDIA-Nemotron-Nano-9B-v2 | 8.9B | BF16 | 19.9 GB | RTX A5000 | $0.176/hr |
| NVIDIA-Nemotron-Nano-9B-v2-FP8 | 8.9B | F8_E4M3 | 9.9 GB | RTX 5060 Ti | $0.110/hr |
| NVIDIA-Nemotron-Nano-12B-v2 | 12.3B | BF16 | 27.5 GB | RTX 4080 Super | $0.338/hr |
| NVIDIA-Nemotron-Nano-12B-v2-VL-FP8 | 13.2B | F8_E4M3 | 14.7 GB | RTX 5060 Ti | $0.110/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 (5 models)
- Nemotron Labs (4 models)
- Nemotron-H (3 models)
