Nemotron 3 Ultra TPS calculator
Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.
Calculated for this model
818 cards we hold specifications for
Smallest card that fits
B300
288 GB · Q3_K_M · 92.4 tok/s
Fastest card
B300
92.4 tok/s · 288 GB
Which GPUs can run Nemotron 3 Ultra?
Set the inputs, read the answer
A longer conversation needs more memory, which can push this model off smaller cards.
Hides cards that would only fit the model by compressing it below this point.
3 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
92.4
tok/s
55–148 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 239.6 GB | Q3_K_M | Tight |
|
73.8
tok/s
44–118 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 239.6 GB | Q3_K_M | Tight |
|
73.8
tok/s
44–118 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 239.6 GB | Q3_K_M | Tight |
Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.
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
- 4 June 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, Question answering
- 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
- 550B
- Training data
- tokens
"550B total parameters with up to 55B active per token" from https://docs.nvidia.com/nemotron/nightly/usage-cookbook/Nemotron-3-Ultra-Base/README.html
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 6.6 × 10²⁴ FLOP
55 billion active parameters, ~20T tokens
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (unrestricted)
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
- Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- Last updated
- 8 June 2026
The extremes
The ten fastest GPUs that run Nemotron 3 Ultra
Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.
The smallest GPUs that still run Nemotron 3 Ultra
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
What the numbers mean
What it takes to run this model
Minimum card
B300
Memory needed
239.6 GB
Fastest
92.4 tok/s
Nemotron 3 Ultra reaches a parameter count of 550B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 3.
The smallest card that holds it is B300, with a memory capacity of 288 GB, running it at a compression of Q3_K_M and producing around 92.4 tokens per second.
At the other end sits B300, generating roughly 92.4 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.
Where it came from
Nemotron 3 Ultra was published by NVIDIA, in the country recorded as United States of America, during June 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, Question answering.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.
Understanding the speeds
Half the cards that hold it manage more than 73.8 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 3 of them.
Because it routes each token through a subset of its weights, it produces text at the pace of a much smaller model. The catch is memory: all of it still has to fit, so the speed is a bonus rather than a discount on hardware.
Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.
What went into building it
The training run consumed about 6.6 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Its inclusion criterion: discretionary.
Step by step
How to choose a GPU for Nemotron 3 Ultra
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Check what it needs before anything else
Start from what it actually needs, which is the requirement of Nemotron 3 Ultra, needing around 239.6 GB at a compression of Q3_K_M. Capacity is the gate — a card either holds it or it does not.
-
02
Decide how long your conversations run
Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting Nemotron 3 Ultra.
-
03
Decide how much compression you will accept
Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
-
04
Rank by throughput rather than spec sheet
Sort by speed to see how cards rank for Nemotron 3 Ultra. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B300, at 92.4 tok/s.
-
05
Check the fit verdict before buying
A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Nemotron 3 Ultra. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
-
06
Check the card from the other side
Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for Nemotron 3 Ultra.
Answers
Nemotron 3 Ultra — common questions
Nemotron 3 Ultra— when was it released?
It was published in June 2026.
Nemotron 3 Ultra— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Nemotron 3 Ultra— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
Nemotron 3 Ultra— how much compute was used to train it?
Training consumed around 6.6 × 10²⁴ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
Nemotron 3 Ultra— can I run it if it does not fit in my GPU?
Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 73.2 GB. Every figure here assumes the whole model is resident on the card.
Nemotron 3 Ultra— would two GPUs run it faster?
Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 3. So a second card is rarely the answer here.
Nemotron 3 Ultra— why does the quantisation differ between cards?
Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
Nemotron 3 Ultra— how accurate are these speed estimates?
They are calculated from specifications rather than measured, and each carries a range. One example: 55–148 tok/s on B300. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
Nemotron 3 Ultra— what GPU do I need to run it?
The smallest card in our catalogue that holds it is B300, with a memory capacity of 288 GB. It runs the model at a compression of Q3_K_M using about 239.6 GB, and produces roughly 92.4 tokens per second. The number of cards able to run it in total: 3.
Nemotron 3 Ultra— how fast is it on a GPU?
It depends on the card. The quickest we calculate is B300, at about 92.4 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 3.
Nemotron 3 Ultra— how much VRAM does it need?
It needs about 239.6 GB at a compression of Q3_K_M, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.
Nemotron 3 Ultra— is it open source?
Its weights are published, so it can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
Nemotron 3 Ultra— how many parameters does it have?
It has a parameter count of 550B. "550B total parameters with up to 55B active per token" from https://docs.nvidia.com/nemotron/nightly/usage-cookbook/Nemotron-3-Ultra-Base/README.html. 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.
Nemotron 3 Ultra— who created it?
It was published by NVIDIA, based in United States of America, an organisation categorised as industry.
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.