Can I run Nemotron 3 Super locally?

Yes, the weights are open and available on Hugging Face under the NVIDIA Nemotron Open Model License, but the minimum requirement is 2× H100-80GB GPUs, so this is a data-centre or high-end workstation deployment, not a consumer machine.

What does Nemotron 3 Super cost via API, and what is the context window?

Pricing is $0.08 per million input tokens and $0.45 per million output tokens; the context window extends to 1 million tokens.

How does Nemotron 3 Super differ from the Nemotron Nano?

The Super model adds Multi-Token Prediction layers for faster generation and better quality, and is trained with NVFP4 quantization; the Nano model does not include MTP and targets smaller deployment footprints.

▲

70.4%

this week

Nemotron 3 Super

8885°

#llm #nvidia #reasoning #agents #coding #long context

This month

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 | $0.08/M input, $0.45/M output. NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for…NVIDIA | 262,144 token context | $0.08/M input, $0.45/M output. NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified. Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

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

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

How much VRAM do I actually need for local AI?

How to Install Ollama and Run a Local AI (Windows, Mac, Linux)

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 Super is NVIDIA's 120B-parameter hybrid MoE model that keeps only 12B parameters active at inference, making it far cheaper to run than its total size suggests. Its Mamba-Transformer architecture with multi-token prediction pushes generation speed well above typical open models of comparable capability. It suits teams building multi-agent pipelines, long-document workflows, or high-volume automation who want open weights they can actually deploy on their own hardware.

Known for

1M token context window built for cross-document reasoning and multi-step agent tasks
Only 12B active parameters at inference despite 120B total — serious efficiency gain
Multi-token prediction layers deliver over 50% faster generation than comparable open models
Reasoning mode is switchable on or off via a single chat template flag
Weights, datasets, and training recipes all published under the NVIDIA Nemotron Open Model License

Watch out for

Minimum hardware requirement is 2× H100-80GB GPUs — this is not a consumer local model.
The NVIDIA Nemotron Open Model License is not a standard open-source licence; check its terms before commercial deployment.
Pre-training data cuts off June 2025; post-training February 2026 — recent events will be missing.

Best for

Prompts to try

Multi-step agent plan

You are an IT automation agent. A user reports: their VPN client connects but all DNS queries time out, only on the corporate network, only since a firmware update to their router yesterday. Diagnose the likely causes in order of probability, then write a step-by-step remediation plan an L1 technician can follow without escalation.

Cross-document reasoning

Here are three quarterly earnings call transcripts from the same company spanning 18 months. Identify any forward guidance given in the first two calls, then assess whether the third call's results confirmed, missed, or exceeded each commitment. Flag any guidance that was quietly dropped without explanation.

Hard coding task

Write a Python function that takes an arbitrary JSON schema and a list of Python dicts, validates each dict against the schema, and returns two lists: valid records and invalid records with a per-field error message. Do not use any third-party libraries. Include edge cases for nested objects and arrays in your tests.

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
NVIDIA Nemotron 3 Ultra 550B A55B
Open-weights model
262,144 token context · $0.50/M input, $2.20/M output
NVIDIA Nemotron 3 Super 120B A12B
Open-weights model
262,144 token context · $0.09/M input, $0.40/M output

More text models from nvidia

Questions people ask

Can I run Nemotron 3 Super locally?: Yes, the weights are open and available on Hugging Face under the NVIDIA Nemotron Open Model License, but the minimum requirement is 2× H100-80GB GPUs, so this is a data-centre or high-end workstation deployment, not a consumer machine.
What does Nemotron 3 Super cost via API, and what is the context window?: Pricing is $0.08 per million input tokens and $0.45 per million output tokens; the context window extends to 1 million tokens.
How does Nemotron 3 Super differ from the Nemotron Nano?: The Super model adds Multi-Token Prediction layers for faster generation and better quality, and is trained with NVFP4 quantization; the Nano model does not include MTP and targets smaller deployment footprints.

Captain's verdict
A serious open agentic model — the active-parameter efficiency is real, but you need data-centre hardware to see it.

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

Also ranked: Bronze · Hottest this month · #72 Hottest AI model · #40 Hottest Text / LLM model · #40 Hottest Text / LLM text model

Not this creator?

Get your own badge

Nemotron 3 Super Popularity Trend

Heat score since 11 Mar 2026

Heat score

8,885°

This week

▲

70.4%

8,815° then, 8,885° now

This month

▲

1,018%

8,567° then, 8,885° now

Past year

n/a

Wasn't released/tracked

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,575°

OpenRouter tokens

1,780,603,688,222 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 178,060 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).

+310°

Adoption rate

About 13,493 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 8,885°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
178,060 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,575°
8,575°
running total
3
Add the adoption rate.
About 13,493 downloads a day right now, measured between two readings, at a quarter of the weight.
+310°
8,885°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,885°

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.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Similar Models

AI Models for Image, Video & Text Generation

Nemotron 3 Super 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 long context local

Browse by Model Family