NOUMENOpen app
NOUMEN

nvidia · Open weights

Nvidia Nemotron 3 Nano 30B

Added Mar 1, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Nvidia's latest Nemotron 3 Nano model with 30B total parameters (3B active) using hybrid Mamba-Transformer MoE architecture. Features excellent throughput and strong reasoning capabilities.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.17
Output
$0.68

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
—
Average output (7 days)
564 tokens
Longer than 53% of 468 models

Side by side

Nvidia Nemotron 3 Nano 30B compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Nvidia Nemotron 3 Nano 30BnvidiaThis modelGemini 2.5 Flash LiteGoogleRemove
ProvidernvidiaGoogle
Discovery tierOpen weightsEfficient
AddedMar 1, 2026Jun 17, 2025
Limits
Context window262.14K1.05MBest
Max output—65.54K
Average output564 tokens42 tokens
Pricing, USD per 1M tokens
Input$0.17$0.10Best
Output$0.68$0.40Best
Cache read—$0.01
Performance
Throughput—271.6 tok/s
Time to first token—0.7 s
Request success (24h)100.0%Best99.4%
Benchmark indexes
Intelligence Index6.8Best6.7
Math Index13.335.3Best
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effort—low, medium, high

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Nvidia Nemotron 3 Nano 30B
  • Gemini 2.5 Flash Lite

Intelligence Index

  • Nvidia Nemotron 3 Nano 30B6.8
  • Gemini 2.5 Flash Lite6.7

Nvidia Nemotron 3 Nano 30B: Better than 8% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Nvidia Nemotron 3 Nano 30B: 13.3
    • Gemini 2.5 Flash Lite: 35.3Top

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Nvidia Nemotron 3 Nano 30B: 10.7%
    • Gemini 2.5 Flash Lite: 32.0%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Nvidia Nemotron 3 Nano 30B: 4.6%Top
    • Gemini 2.5 Flash Lite: 3.7%

  • GPQA Diamond

    Graduate-level science questions

    • Nvidia Nemotron 3 Nano 30B: 39.9%
    • Gemini 2.5 Flash Lite: 47.4%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Nvidia Nemotron 3 Nano 30B: 57.9%
    • Gemini 2.5 Flash Lite: 72.4%Top

  • IFBench

    Following precise output instructions

    • Nvidia Nemotron 3 Nano 30B: 37.5%Top
    • Gemini 2.5 Flash Lite: 31.5%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Nvidia Nemotron 3 Nano 30B: 36.0%
    • Gemini 2.5 Flash Lite: 40.0%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Nvidia Nemotron 3 Nano 30B: 13.3%
    • Gemini 2.5 Flash Lite: 35.3%Top

  • AIME

    Competition mathematics

    • Nvidia Nemotron 3 Nano 30B: —
    • Gemini 2.5 Flash Lite: 50.0%

  • MATH-500

    Competition math problems

    • Nvidia Nemotron 3 Nano 30B: —
    • Gemini 2.5 Flash Lite: 92.6%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Nvidia Nemotron 3 Nano 30B: 12.1%Top
    • Gemini 2.5 Flash Lite: 2.3%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Nvidia Nemotron 3 Nano 30B: 25.4%Top
    • Gemini 2.5 Flash Lite: 19.0%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Nvidia Nemotron 3 Nano 30B: 10.7%
    • Gemini 2.5 Flash Lite: 32.0%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Request success (24h)
100.0%
Reliable
Hourly request success · last 72 hoursLowest hour 94.7%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-nano-30b-a3b",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="nvidia/nemotron-3-nano-30b-a3b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

nvidia

Other nvidia models, starting with the same family.