Model profile
NVIDIA

NVIDIA: Nemotron 3 Nano 30B A3B

NVIDIA: Nemotron 3 Nano 30B A3B is a budget-priced text-first model from NVIDIA with fast runtime profile, large context posture, and the clearest fit around long-context research / agent workflows.

Best for: Long-context research / Agent workflowsFast latencyLarge contextBudget pricing
Intelligence
13.2

Benchmark blend

Coding
15.8

Dev workflow signal

Context
262K Tokens

Large

Input Price
$0.05

Budget tier

Decision snapshot
48

NVIDIA: Nemotron 3 Nano 30B A3B currently reads as a budget text-first option with large context and a fast runtime profile.

Overall profile
Use-case specific
Best for
Long-context research / Agent workflows
Latency tier
Fast
Price tier
Budget
Source coverage
OpenRouterArtificial Analysis

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
13.2
13

General reasoning and benchmark headroom.

Limited
Speed
70 tok/s
75

TTFT 0.27s

Competitive
Context
262K Tokens
88

How much prompt and task state can stay in view.

Above average
Price
$0.05
86

$0.20 output / 1M

Efficient

Editorial Profile

NVIDIA: Nemotron 3 Nano 30B A3B in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Use-case specificCoding score 16Math score 13

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...

Identity

NVIDIA text-first profile

Positioning

Long-context research / Agent workflows with large context and fast runtime.

Cost posture

Efficient spend profile. More comfortable for sustained prompt volume if the capability fit is right.

Strengths
  • Large context headroom supports repo-wide prompts and long research sessions.

  • Latency and throughput look responsive enough for interactive loops.

Tradeoffs
  • Budget-friendly input pricing is a strength, but raw capability may vary by workload.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

Best fit
  • Long-context summarization, repo analysis, and policy or document review.

Explore Next

Similar profiles worth opening next

NVIDIA

NVIDIA: Nemotron 3 Super

Intelligence
36.0
Context
262K Tokens
Input Price
$0.10
NVIDIA

Nemotron Cascade 2 30B A3B

Intelligence
27.7
Context
N/A
Input Price
$0.00
NVIDIA

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

Intelligence
24.3
Context
N/A
Input Price
$0.06

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

General intelligence

Broad reasoning, knowledge depth, and flagship benchmark posture.

Intelligence Index
13.2
MMLU Pro
57.9%
GPQA
39.9%
HLE
4.6%
Coding

Software implementation, debugging quality, and coding benchmark signal.

Coding Index
15.8
LiveCodeBench
0.360
SciCode
23.0%
Math

Formal reasoning, structured problem solving, and competition-style math.

Math Index
13.3
AIME 2025
13.3%
Agent / tool use

Long-horizon execution quality and interactive benchmark evidence.

IFBench
37.5%
TAU2
25.4%
TerminalBench Hard
12.1%
LCR
6.7%

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
262K Tokens
Vision
Text-first
Modalities
text
Tokenizer
Other
Moderation
No
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p
Input Modalities
text
Output Modalities
text
Price architecture
Input
per 1M input tokens
$0.05
Output
per 1M output tokens
$0.20
Blended
AA 3:1 mix
$0.09

This model is relatively efficient on price. It is the easier fit when sustained prompt volume matters.

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.