LLM Reference
NVIDIA NIM

Nemotron 3 Nano on NVIDIA NIM

Nemotron-3 · NVIDIA AI

Serverless

Pricing

TypePrice (per 1M)
Input tokensFree
Output tokensFree

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

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

Released2026-03-16
Parameters3.97B
Context256K
ArchitectureMixture of Experts

Related Models on NVIDIA NIM