Nemotron 3 Nano on NVIDIA NIM

Nemotron 3 · NVIDIA AI

ServerlessOpen Weights

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.

Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: nvidia/nemotron-3-nano-30b-a3b
Model ID
nvidia/nemotron-3-nano-30b-a3b

Request example

Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID nvidia/nemotron-3-nano-30b-a3b.

Gotchas

  • Use provider model ID "nvidia/nemotron-3-nano-30b-a3b", not the LLMReference slug "nemotron-3-nano".

Capabilities

JSON / Tool use

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.

Get Started

Model Specs

Released2025-12-15
Parameters3.97B
Context256k
ArchitectureMixture of Experts