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
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 for 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
At 550B parameters, Nemotron 3 Ultra is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 3 of the cards we track can hold it on their own, and all of them are datacentre parts.
The smallest card that holds it is the B300 with 288 GB, running it at Q3_K_M and producing around 92.4 tokens per second.
At the other end, a B300 generates roughly 92.4 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.
Where it came from
Nemotron 3 Ultra was published by NVIDIA, in United States of America, in June 2026. The organisation is categorised as industry.
It works in Language, and is recorded as doing 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, and 3 exceed reading speed outright.
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 describes the cost of creating it and has no bearing on how quickly it generates text.
Its inclusion criterion is 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
Look at what Nemotron 3 Ultra actually needs — around 239.6 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
-
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 Nemotron 3 Ultra stops fitting a card that seemed fine.
-
03
Decide how much compression you will accept
Compression is what makes Nemotron 3 Ultra fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
-
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 — generation is bound by memory bandwidth, which is why the B300 tops it at 92.4 tok/s.
-
05
Check the fit verdict before buying
A tight fit runs Nemotron 3 Ultra but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
-
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. Worth a look before buying for Nemotron 3 Ultra alone — a card is usually bought for more than one model.
Answers
Nemotron 3 Ultra — common questions
When was Nemotron 3 Ultra released?
Nemotron 3 Ultra was published in June 2026.
What is Nemotron 3 Ultra used for?
Nemotron 3 Ultra works in Language, and is recorded as handling language modeling/generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Where can I download Nemotron 3 Ultra?
The weights for Nemotron 3 Ultra are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
How much compute was used to train Nemotron 3 Ultra?
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.
Can I run Nemotron 3 Ultra if it does not fit in my GPU?
Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 73.2 GB. Our figures for Nemotron 3 Ultra assume it is fully resident.
Would two GPUs run Nemotron 3 Ultra faster?
Capacity adds across cards; throughput does not. Since 3 of the cards we track already hold Nemotron 3 Ultra on their own, a second card is rarely the answer here.
Why does the quantisation differ between cards for Nemotron 3 Ultra?
Because capacity varies, so does how hard Nemotron 3 Ultra has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.
How accurate are these Nemotron 3 Ultra speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 55–148 tok/s on the B300, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
What GPU do I need to run Nemotron 3 Ultra?
The smallest card in our catalogue that holds Nemotron 3 Ultra is the B300, with 288 GB of memory. It runs the model at Q3_K_M using about 239.6 GB, and produces roughly 92.4 tokens per second. 3 cards in total can run it.
How fast is Nemotron 3 Ultra on a GPU?
It depends on the card. The quickest we calculate is a 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 3 of the cards that can run Nemotron 3 Ultra clear that.
How much VRAM does Nemotron 3 Ultra need?
About 239.6 GB at Q3_K_M compression, 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.
Is Nemotron 3 Ultra open source?
Its weights are published, so Nemotron 3 Ultra 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.
How many parameters does Nemotron 3 Ultra have?
Nemotron 3 Ultra has 550B parameters. "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.
Who created Nemotron 3 Ultra?
Nemotron 3 Ultra was published by NVIDIA, based in United States of America, 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.