Skip to content

NVIDIA · Chat

Nemotron 3 Nano 30B A3B

NVIDIA 🇺🇸ChatOpen weights. One of its sources says the weights are publicly available.
From Venice's listing:
NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.
llminfo IQ
109.7
Market median price
$0.105 blended / 1M
Max context
1M
Listings
29

Evidence and sources

🤗 nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16llminfo IQ 109.7, ranked among chat models. From 137 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 91.4, 95% interval 77–106. From 7 benchmark families across 3 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (36.7). Costs more per task than its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 6 Dec 2025Maker HQ: US (source)
All rankings: #3 in Hacker News discussions this week #198 on OpenRouter this week #242 on OpenRouter this month #265 on OpenRouter today #438 on NanoGPT recentlyAll rankings: #3 in Hacker News discussions this week #198 on OpenRouter this week #242 on OpenRouter this month #265 on OpenRouter today #438 on NanoGPT recentlySources: LMArena data, Models.dev data, AI/ML API data, Venice.ai data, Hugging FacePrimary data from LMArena from Models.dev: name, weights availability from AI/ML API: primary mode from Venice.ai: description from Hugging Face: release date
Tags from its sources:instructtoolsreasoningopen-sourcemoecodingfunction-calling

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 2 of the 6 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 5 maker's prices; 5 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt cachingWeb search

Listings

 Flowdotnvidia/nemotron-3-nano-30b-a3b:free · freeSource: FlowDot data256K$0.00$0.00
 Eden AIInference by DeepInfradeepinfra/nvidia/Nemotron-3-Nano-30B-A3BSource: Models.dev data262K$0.05cache read $0.025$0.20
 NanoGPTnvidia/nemotron-3-nano-30b-a3bSources: Models.dev data, NanoGPT262K$0.05cache read $0.025$0.20
 RequestyInference by DeepInfradeepinfra/nvidia/Nemotron-3-Nano-30B-A3BSource: Requesty data262K$0.05$0.20
 Crusoenvidia/NVIDIA-Nemotron-3-Nano-30B-A3BSource: Models.dev data262K$0.05cache read $0.03$0.20
 DeepInfradeepinfra/nvidia/Nemotron-3-Nano-30B-A3BSources: LiteLLM data, Models.dev data262K$0.05cache read $0.025$0.20
 Merge Gatewaynvidia/nemotron-3-nano-30b-a3bSource: Models.dev data256K$0.05$0.20
 Novita AInvidia/nemotron-3-nano-30b-a3bSources: LiteLLM data, Models.dev data, Novita AI data262K$0.05$0.20
 Cortecs AInvidia-nemotron-3-nano-30b-a3bSources: Cortecs EU Router data, Models.dev data256K
 Hugging FaceInference by Nebius AI Studionvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 · bf16Source: Hugging Face Inference Providers data262K$0.06$0.24
Show all 22 listings

Showing 10 of 22: the cheapest per 1M input tokens from each provider.

Also sold by Aihubmix, Eurouter, Infomaniak, Kilo, Nebius AI Studio, Nous Portal, OpenRouter, Thinking Machines, Venice.

7 listings without a price are hidden.

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO45 related benchmarks · 45 results
Arena ELO
Source: LMArena data · Nov 2026
Arena-Hard v2
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Chinese
Source: LMArena data · Nov 2026
Creative Writing
Source: LMArena data · Nov 2026
English
Source: LMArena data · Nov 2026
Exclude Ties
Source: LMArena data · Nov 2026
Show 39 more resultsHide 39 results
Expert
Source: LMArena data · Nov 2026
French
Source: LMArena data · Nov 2026
German
Source: LMArena data · Nov 2026
Hard Prompts
Source: LMArena data · Nov 2026
Hard Prompts English
Source: LMArena data · Nov 2026
Industry Mathematical
Source: LMArena data · Nov 2026
Industry Medicine and Healthcare
Source: LMArena data · Nov 2026
Industry Software and It Services
Source: LMArena data · Nov 2026
Japanese
Source: LMArena data · Nov 2026
Korean
Source: LMArena data · Nov 2026
Longer Query
Source: LMArena data · Nov 2026
Multi Turn
Source: LMArena data · Nov 2026
Non English
Source: LMArena data · Nov 2026
Polish
Source: LMArena data · Nov 2026
Russian
Source: LMArena data · Nov 2026
Spanish
Source: LMArena data · Nov 2026
Style-Controlled
Source: LMArena data · Nov 2026
Text Factuality
Source: LMArena data · Nov 2026
Text Factuality - Chinese
Source: LMArena data · Nov 2026
Text Factuality - Creative Writing
Source: LMArena data · Nov 2026
Text Factuality - English
Source: LMArena data · Nov 2026
Text Factuality - Exclude Ties
Source: LMArena data · Nov 2026
Text Factuality - Hard Prompts
Source: LMArena data · Nov 2026
Text Factuality - Longer Query
Source: LMArena data · Nov 2026
Text Factuality - Multi Turn
Source: LMArena data · Nov 2026
Text Factuality - Non English
Source: LMArena data · Nov 2026
Text Factuality - Russian
Source: LMArena data · Nov 2026

Multilingual

WMT24++Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Agentic

Tau2 Retail4 related benchmarks · 7 results
Tau2 Retail
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Tau2 Airline
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Tau2 Telecom
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
tau2-bench airline
Source: OpenRouter benchmark exports
nemotron-3-nano-30b-a3b · 90-day results
Across 3 providers lowest 47.3% median 48% highest 48.9%OpenRouter's automatic routing 50.9%
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • Nebius
  • DeepInfra
  • Crusoe

Coding

SciCodeSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond5 results
Source: OpenRouter benchmark exports
nemotron-3-nano-30b-a3b · 90-day results
Across 4 providers lowest 59.6% median 63.1% highest 68.1%OpenRouter's automatic routing 63.1%
Show results from 4 providers and OpenRouter's automatic routingHide results from 4 providers and OpenRouter's automatic routing
  • DeepInfra
  • Crusoe
  • OpenRouter's automatic routing
  • Nebius
  • Novita

Instruction following

Math

AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Factuality

Knowledge

MMLU-ProSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MMLU-ProXSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Reasoning

Other

Horangi36 related benchmarks · 36 results
4: ALT_환각방지
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: haerae_bench_v1_rc
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: haerae_bench_v1_wo_rc
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: hrm8k
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: kmmlu
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: kmmlu_pro
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Show 30 more resultsHide 30 results
4 subset: ko_aime2025
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: ko_arc_agi
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: ko_balt_700_semantic
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: ko_balt_700_syntax
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: ko_hallulens_nonexistent
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: ko_hallulens_wikiqa
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: ko_hle
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: ko_moral
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: ko_truthful_qa
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: kobbq
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: korean_hate_speech
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4 subset: squad_kor_v1
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: ALT_유해성방지
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: ALT_윤리/도덕
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: ALT_제어성
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: ALT_편향성방지
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: FINAL_SCORE
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_구문해석
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_논리적추론
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_수학적추론
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_의미해석
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_일반적지식
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_전문적지식
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_정보검색
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_추상적추론
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_코딩능력
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_표현
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: GLP_함수호출
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: 가치정렬성능(ALT)_AVG
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4: 범용언어성능(GLP)_AVG
Source: Horangi Korean Leaderboard 4 data docs
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Data credits: Data by LLM Stats · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · LMArena, CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · Hugging Face official benchmark leaderboards; licence varies by benchmark · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Shaberi v2.1, Shisa.AI, Apache-2.0. GPT-5.1-judge scores only; judges are not comparable. (licence) · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Around the web

Also known as: deepinfra/nvidia/nemotron-3-nano-30b-a3b, nebius/nvidia/nvidia-nemotron-3-nano-30b-a3b, novita/nvidia/nemotron-3-nano-30b-a3b, nvidia-nemotron-3-nano-30b-a3b, nvidia-nemotron-3-nano-30b-a3b-bf16, nvidia/nemotron-3-nano-30b-a3b, nvidia/nemotron-3-nano-30b-a3b:free, nvidia/nvidia-nemotron-3-nano-30b-a3b, nvidia/nvidia-nemotron-3-nano-30b-a3b-bf16, nvidia/nvidia-nemotron-3-nano-30b-a3b-fp8, nvidia_nim/nvidia/nemotron-nano-3-30b-a3b

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works