Nvidia
NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
| Specifications | |
|---|---|
| Provider | Nvidia |
| Input pricing | $0.05/M tokens |
| Output pricing | $0.20/M tokens |
| Context length | 262K tokens |
| Max output | 228K tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | Other |
| Content moderated | No |
| HuggingFace | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 |
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p