Can I run Nemotron 3 Nano 30B A3B locally?

Yes — weights are fully open and available on Hugging Face under the NVIDIA Nemotron Open Model License. At 30B total parameters you will need substantial VRAM for full-precision inference, though the MoE design means only 3.5B parameters are active per token.

What does it cost to use via API, and what is the context limit?

NVIDIA lists $0.06 per million input tokens and $0.24 per million output tokens, with a 262,144-token context window.

How does this compare to Qwen3-30B-A3B?

Both share the same active-parameter count and MoE scale. Nemotron leads on agentic tasks (SWE-Bench, BFCL, Arena-Hard average) and formal math (MiniF2F); Qwen3-30B-A3B leads on long-context retrieval (AA-LCR) and general knowledge (MMLU-Pro). Nemotron also ships with open training data and recipes, which Qwen3 does not.

Nemotron 3 Nano 30B A3B

3117°

#llm #nvidia #reasoning #agents #coding #local

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

NVIDIA | 262,144 token context | $0.06/M input, $0.24/M output. 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 open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

Guides for this model

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

Open weights vs open source vs API-only: what you are actually allowed to do

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Nemotron 3 Nano 30B A3B is a Mixture-of-Experts model from NVIDIA that keeps only 3.5B parameters active per token while drawing on 30B total, making it unusually efficient for its capability tier. It is built specifically for agentic workflows and supports togglable reasoning traces. Weights, datasets, and training recipes are all open, so you can fine-tune and self-host it without asking permission.

Known for

Togglable chain-of-thought: reasoning traces on or off per request.
Strong agentic benchmarks, including SWE-Bench and BFCL function-calling scores.
MoE architecture activates only 3.5B of 30B parameters per token for low compute cost.
262k-token context window with solid RULER retrieval scores.
Fully open: weights, datasets and training recipes all published.

Watch out for

Governed by the NVIDIA Nemotron Open Model License, not a permissive Apache or MIT licence — read it before deploying.
Long-context retrieval (AA-LCR) lags behind Qwen3-30B-A3B noticeably; don't lean on it for deep needle-in-haystack tasks.
30B total parameters means you need meaningful VRAM to run it locally at full precision.

Best for

Prompts to try

Debug a failing agent tool

I have a Python agent that calls a weather API and then writes a summary to a file. It silently fails when the API returns a 429. Walk me through how to add retry logic with exponential backoff, handle the rate-limit error gracefully, and log failures without crashing the agent loop. Show the revised code.

Hard math proof check

Prove that for any integer n greater than 1, n^5 - n is divisible by 30. Show each step of the reasoning, identify which prime factors you are handling separately, and confirm the result holds for n = 2, 3, and 6 as a sanity check.

Plan a multi-step research task

You are an agent with access to a web search tool and a code execution tool. Outline a step-by-step plan to determine which of the five largest open-weight language models released in 2025 has the lowest cost per useful output token on coding tasks. Specify what each tool call does and what decision gates exist between steps.

Compare with

Nemotron 3 Ultra
Open-weights model
262,144 token context · $0.60/M input, $2.40/M output
Nemotron 3.5 Lightning
Open-weights model
262,144 token context · $0.07/M input, $0.20/M output
Nemotron 3 Super
Open-weights model
262,144 token context · $0.08/M input, $0.45/M output
NVIDIA Nemotron 3 Ultra 550B A55B
Open-weights model
262,144 token context · $0.50/M input, $2.20/M output

More text models from nvidia

Questions people ask

Can I run Nemotron 3 Nano 30B A3B locally?: Yes — weights are fully open and available on Hugging Face under the NVIDIA Nemotron Open Model License. At 30B total parameters you will need substantial VRAM for full-precision inference, though the MoE design means only 3.5B parameters are active per token.
What does it cost to use via API, and what is the context limit?: NVIDIA lists $0.06 per million input tokens and $0.24 per million output tokens, with a 262,144-token context window.
How does this compare to Qwen3-30B-A3B?: Both share the same active-parameter count and MoE scale. Nemotron leads on agentic tasks (SWE-Bench, BFCL, Arena-Hard average) and formal math (MiniF2F); Qwen3-30B-A3B leads on long-context retrieval (AA-LCR) and general knowledge (MMLU-Pro). Nemotron also ships with open training data and recipes, which Qwen3 does not.

Captain's verdict
A genuinely open, agent-first MoE that punches above its active-parameter weight — worth a look if you self-host reasoning pipelines.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

TEXT / LLM

Fugu Ultra

TEXT / LLM

AI Models for Image, Video & Text Generation

Nemotron 3 Nano 30B A3B is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm nvidia reasoning agents coding local long context

Browse by Model Family