Nemotron models
5 Nemotron models on Hugging Face, from 618M to 31.6B parameters. At the precision each one is published in, the smallest needs about 2.8 GB of VRAM (nemotron-speech-streaming-en-0.6b, cheapest live fit: V100) and the largest about 70.6 GB (Nemotron-Cascade-2-30B-A3B, cheapest live fit: A100). The cheapest way to run nemotron-speech-streaming-en-0.6b is $0.088/hr.
Nemotron models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| nemotron-speech-streaming-en-0.6b | 618M | F32 | 2.8 GB | V100 | $0.088/hr |
| NVIDIA-Nemotron-Parse-v1.1 | 957M | F32 | 4.3 GB | V100 | $0.088/hr |
| nemotron3-8b | 8.5B | BF16 | 19.1 GB | RTX A5000 | $0.176/hr |
| NVIDIA-NemotronLabs-VoiceChat-11B | 11.1B | F32 | 49.6 GB | A100 | $1.21/hr |
| Nemotron-Cascade-2-30B-A3B | 31.6B | BF16 | 70.6 GB | A100 | $1.21/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 Labs (4 models)
- Nemotron-H (3 models)
