Nemotron 3 Ultra
9290°
Run this model
Offers / Ads
NVIDIA | 262,144 token context | $0.60/M input, $2.40/M output. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks. It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.
Guides for this model
How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading
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?
Best local LLM by use case (October 2026): the right open model for every job
How to Install Ollama and Run a Local AI (Windows, Mac, Linux)
Captain's notes
Notes from 2026-10-13
Nemotron 3 Ultra is NVIDIA's frontier reasoning and agent-orchestration model: 550B total parameters, 55B active, built on a hybrid LatentMoE architecture that blends Mamba-2, MoE, and Attention layers. Weights are open under the OpenMDW 1.1 licence, and reasoning can be toggled on or off at inference time. It suits teams running high-volume agentic pipelines, long-context analysis, or complex coding and research workflows at scale.
Known for
- Configurable reasoning mode: toggle chain-of-thought on or off per request.
- Up to 1M token context window for long-document and multi-turn agent work.
- Multi-Token Prediction layers for faster generation without quality loss.
- Ten supported languages including Japanese, Hindi, Korean and Chinese.
- Open weights with a commercial-use licence, runnable on your own infrastructure.
Watch out for
- Minimum hardware is 8× GB200/B200 or 16× H100 GPUs — this is not a laptop model.
- Licensed under OpenMDW 1.1, not Apache or MIT; check the terms before deploying commercially.
- API output pricing at $2.40/M tokens adds up fast in high-volume reasoning pipelines.
Prompts to try
Multi-step coding agent
You are given a Python monorepo with no documentation. Write a plan to: (1) map all public API endpoints across services, (2) identify any endpoints that share no authentication middleware, (3) generate a Markdown report listing each gap with the file path and line number. Then implement step 1 as a working Python script.
Deep research synthesis
I am pasting the full text of three conflicting academic papers on mRNA vaccine stability at room temperature. Read all three, identify the specific experimental conditions where their results diverge, propose a hypothesis that reconciles the divergence, and list the follow-up experiments that would test it. Papers: [paste here]
Complex planning under constraints
A logistics company must route 12 delivery trucks across 80 stops in a city. Trucks have different capacity limits, three stops require refrigerated vehicles, two stops have time windows before 9 am, and fuel cost must stay under a fixed daily budget. Outline a step-by-step optimisation approach, identify which constraints are hardest to satisfy simultaneously, and describe the trade-offs.
Compare with
- Nemotron 3.5 LightningOpen-weights model262,144 token context · $0.07/M input, $0.20/M output
- Nemotron 3 SuperOpen-weights model262,144 token context · $0.08/M input, $0.45/M output
- NVIDIA Nemotron 3 Ultra 550B A55BOpen-weights model262,144 token context · $0.50/M input, $2.20/M output
- NVIDIA Nemotron 3 Super 120B A12BOpen-weights model262,144 token context · $0.09/M input, $0.40/M output
More text models from nvidia
Questions people ask
- Can I run Nemotron 3 Ultra locally?
- Yes, the weights are open and hosted on Hugging Face under the OpenMDW 1.1 licence, but the minimum requirement is 8× GB200 or 16× H100 GPUs, so local deployment means a serious server rack, not a workstation.
- What does it cost and how long is the context?
- Via API it is $0.60 per million input tokens and $2.40 per million output tokens. The context window goes up to 1 million tokens.
- How does Nemotron 3 Ultra differ from other large MoE models?
- Its LatentMoE architecture mixes Mamba-2 state-space layers with MoE and Attention layers, and it adds Multi-Token Prediction for faster generation — a combination NVIDIA says is optimised specifically for high-throughput agentic pipelines rather than general chat.
Captain's verdictA serious open-weights frontier model for teams who own the hardware and need long-context agent pipelines at scale — not a casual API pick.
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.
Also ranked: #6 Hottest Text / LLM model · #6 Hottest Text / LLM text model
Not this creator?
Get your own badge
Nemotron 3 Ultra Popularity Trend
Heat score since 4 Jun 2026
Heat score
9,290°
This week
▲
23.3%
9,261° then, 9,290° now
This month
▲
169%
9,157° then, 9,290° 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.
+1,923°
OpenRouter tokens
25,819,029,435,213 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, 2,581,902 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).
+367°
Adoption rate
About 77,596 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 9,290°, 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.
- 1Start 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
- 2Add the downloads.2,581,902 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.+1,923°8,923°running total
- 3Add the adoption rate.About 77,596 downloads a day right now, measured between two readings, at a quarter of the weight.+367°9,290°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.9,290°
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.
Nemotron 3 Ultra 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.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153