NVIDIA

Nemotron 3 Nano 30B A3B

by NVIDIAtext->text4 endpoints
Neura Intelligence Index
39.9/ 100
Rank
#223
Confidence
medium
Benchmarks
6(15% coverage)

Overview

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...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
262.1K tokens
Max Output
235.9K tokens
Tokenizer
Other
Uptime (24h)
10000.0%
Parameters
32000000000B
License
nvidia_open_model_license_agreementOpen Weights
Country
🇺🇸US
Release Date
December 15, 20259mo

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

coding

BenchmarkScoreSource
SWE-bench Verified
38.8
verified
SciCode
33.3
verified
TerminalBench
8.5
verified

math

BenchmarkScoreSource
AIME 2025
99.2
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
75
verified
Humanity's Last Exam
15.5
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.06
Output$0.24
Added
December 14, 2025
Last synced 9/21/2026