Nemotron 3 Super

Closed weights NVIDIA 120B parameters March 2026

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
NVIDIA
Organisation type
Industry
Country
United States of America
Published
11 March 2026
Authors
Aaron Blakeman, Aaron Grattafiori, Aarti Basant, Abhibha Gupta, Abhinav Khattar, Adi Renduchintala, Aditya Vavre, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek, Aleksandr Shaposhnikov, Alex Kondratenko, Alexander Bukharin, Alexandre Milesi, Ali Taghibakhshi, Alisa Liu, Amelia Barton, Ameya Sunil Mahabaleshwarkar, Amir Klein, Amit Zuker, Amnon Geifman, Amy Shen, Anahita Bhiwandiwalla, Andrew …

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Language modeling/generation, Coding
Numerical format
NVFP4

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
120B

"The new Super model is a 120B total, 12B active-parameter"

Training data
tokens

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Discretionary
Record confidence
Likely

Sources

Where this record came from and when it was last checked.

Reference
Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning
Last updated
10 April 2026

What the numbers mean

What this model is

Nemotron 3 Super was published by NVIDIA, in the country recorded as United States of America, during March 2026. The publishing organisation is categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Coding.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

The reason it appears in this catalogue at all: discretionary.

Answers

Nemotron 3 Super — common questions

01

Nemotron 3 Super— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

02

Nemotron 3 Super— how many parameters does it have?

It has a parameter count of 120B. "The new Super model is a 120B total, 12B active-parameter". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

03

Nemotron 3 Super— who created it?

It was published by NVIDIA, based in United States of America, an organisation categorised as industry.

04

Nemotron 3 Super— when was it released?

It was published in March 2026.

05

Nemotron 3 Super— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Coding. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

Nemotron 3 Super— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

Source

Original publication

Record last updated 10 April 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.