Last refreshed 2026-05-14. Next refresh: weekly.
Why use Nemotron 3 Nano on NVIDIA NIM?
NVIDIA NIM offers Nemotron 3 Nano with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: nvidia/nemotron-3-nano-30b-a3bnvidia/nemotron-3-nano-30b-a3bRequest example
nvidia/nemotron-3-nano-30b-a3b.Gotchas
- Use provider model ID "nvidia/nemotron-3-nano-30b-a3b", not the LLMReference slug "nemotron-3-nano".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
About Nemotron 3 Nano
NVIDIA's lightweight 3.97B parameter model optimized for edge deployment with FP8 quantization (W8A8 mixed precision). Designed for agentic AI applications including gaming NPCs, local voice assistants, and IoT automation. Supports instruction following, tool use, and hallucination avoidance. Strong performance on BFCL, IFBench, IFEval, HaluEval, RULER, Tau2, AIME25, MATH500, GPQA-D, and LiveCodeBench.
FAQ
What is the context window for Nemotron 3 Nano on NVIDIA NIM?
Nemotron 3 Nano supports a 256,000 token context window on NVIDIA NIM.
What API model ID do I use for Nemotron 3 Nano on NVIDIA NIM?
Use the model ID nvidia/nemotron-3-nano-30b-a3b when calling NVIDIA NIM's API.
Who created Nemotron 3 Nano?
Nemotron 3 Nano was created by NVIDIA AI as part of the Nemotron 3 model family.
Is Nemotron 3 Nano open source?
Nemotron 3 Nano is open source under Apache 2.0 according to the seed data.