Nemotron 3-Nano-30B-A3B TPS calculator

Open weights NVIDIA 31.6B parameters December 2025

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

241 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Xeon Phi 7120P

16 GB · Q3_K_M · 46.0 tok/s

Fastest card

B200

596 tok/s · 180 GB

Which GPUs can run Nemotron 3-Nano-30B-A3B?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

241 cards match

Calculating

					Needs	Quantisation	Fit
596 tok/s 357–953 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	32.8 GB	Q8_0	Comfortable
596 tok/s 357–953 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	32.8 GB	Q8_0	Comfortable
476 tok/s 285–761 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	32.8 GB	Q8_0	Comfortable
476 tok/s 285–761 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	32.8 GB	Q8_0	Comfortable
380 tok/s 228–609 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	32.8 GB	Q8_0	Comfortable
364 tok/s 218–583 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	32.8 GB	Q8_0	Comfortable
364 tok/s 218–583 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	32.8 GB	Q8_0	Comfortable
348 tok/s 209–558 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	32.8 GB	Q8_0	Comfortable
309 tok/s 186–495 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	32.8 GB	Q8_0	Comfortable
309 tok/s 186–495 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	32.8 GB	Q8_0	Comfortable
309 tok/s 186–495 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	32.8 GB	Q8_0	Comfortable
293 tok/s 176–469 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
250 tok/s 150–400 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
250 tok/s 150–400 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	32.8 GB	Q8_0	Comfortable
250 tok/s 150–400 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
250 tok/s 150–400 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
250 tok/s 150–400 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	32.8 GB	Q8_0	Comfortable
230 tok/s 138–369 · low confidence	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	18.1 GB	Q4_K_M	Tight
227 tok/s 136–363 · low confidence	Tesla V100 SXM2 16 GB NVIDIA	16 GB	1,130 GB/s	Nov 2019	14.4 GB	Q3_K_M	Tight
210 tok/s 126–336 · low confidence	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	18.1 GB	Q4_K_M	Tight
202 tok/s 121–324 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	25.4 GB	Q6_K	Tight
202 tok/s 121–324 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	25.4 GB	Q6_K	Tight
194 tok/s 116–310 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.4 GB	Q6_K	Tight
194 tok/s 116–310 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	25.4 GB	Q6_K	Tight
193 tok/s 116–309 · low confidence	GeForce RTX 5080 NVIDIA	16 GB	960 GB/s	Jan 2025	14.4 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: 15 December 2025
Authors: Abhinav Khattar, Aleksander Ficek, Alisa Liu, Arham Mehta, Asif Ahamed, Ayush Dattagupta, Benedikt Schifferer, Brandon Norick, Branislav Kisacanin, Dan Su, Dane Corneil, Daria Gitman, Dhruv Nathawani, Dima Rekesh, Divyanshu Kakwani, Edgar Minasyan, Eileen Long, Ellie Evans, Eric Tramel, Evelina Bakhturina, Felipe Soares, Feng Chen, Gantavya Bhatt, George Armstrong, Igor Gitman, Ivan Moshkov, Jane …

What it does

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

Domain: Language
Task: Language modeling/generation

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: 31.6B
Training data: tokens

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: 4.8 × 10²³ FLOP

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware: NVIDIA H100 SXM5 80GB

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 (restricted use)
Hugging Face: nvidia

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: NVIDIA Nemotron 3 Family of Models
Last updated: 8 April 2026

The extremes

The ten fastest GPUs that run Nemotron 3-Nano-30B-A3B

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-Nano-30B-A3B

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 you need to run it

Minimum card

Xeon Phi 7120P

Memory needed

14.4 GB

Fastest

596 tok/s

Nemotron 3-Nano-30B-A3B reaches a parameter count of 31.6B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 241.

The least hardware that works is Xeon Phi 7120P, with a memory capacity of 16 GB, running it at a compression of Q3_K_M and producing around 46.0 tokens per second.

Top of the range is B200, generating roughly 596 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Background

Nemotron 3-Nano-30B-A3B was published by NVIDIA, in the country recorded as United States of America, during December 2025. The category the publisher falls under is industry.

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

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. On Hugging Face it is published under the organisation nvidia.

Reading the throughput figures

Across every card that can run it, the middle of the range sits at 94.0 tokens per second. Exceeding reading speed outright: 239 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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

What went into building it

Training it took a computation budget of roughly 4.8 × 10²³ FLOP, on hardware recorded as NVIDIA H100 SXM5 80GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

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

Step by step

How to choose a GPU for Nemotron 3-Nano-30B-A3B

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Start from the memory column

Every card here has been checked against Nemotron 3-Nano-30B-A3B, needing around 14.4 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Match the context to your actual use

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-Nano-30B-A3B.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy, 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

The speed ordering is effectively an ordering by memory bandwidth, for Nemotron 3-Nano-30B-A3B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 596 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage it from those with room to spare, in the case of Nemotron 3-Nano-30B-A3B. 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

See what else that card runs

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-Nano-30B-A3B.

Answers

Nemotron 3-Nano-30B-A3B — common questions

Nemotron 3-Nano-30B-A3B— when was it released?

It was published in December 2025.

Nemotron 3-Nano-30B-A3B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Nemotron 3-Nano-30B-A3B— where can I download it?

Its weights are published on Hugging Face, under the organisation nvidia. We do not host model files — this site calculates what hardware is needed to run them.

Nemotron 3-Nano-30B-A3B— how much compute was used to train it?

Training consumed around 4.8 × 10²³ FLOP, on hardware recorded as NVIDIA H100 SXM5 80GB. 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-Nano-30B-A3B— 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 7.3 GB. Every figure here assumes the whole model is resident on the card.

Nemotron 3-Nano-30B-A3B— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 241. So a second card is rarely the answer here.

Nemotron 3-Nano-30B-A3B— 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: 6. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Nemotron 3-Nano-30B-A3B— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: 357–953 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Nemotron 3-Nano-30B-A3B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Xeon Phi 7120P, with a memory capacity of 16 GB. It runs the model at a compression of Q3_K_M using about 14.4 GB, and produces roughly 46.0 tokens per second. The number of cards able to run it in total: 241.

Nemotron 3-Nano-30B-A3B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 596 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: 239.

Nemotron 3-Nano-30B-A3B— how much VRAM does it need?

It needs about 14.4 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-Nano-30B-A3B— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q3_K_M, using about 14.4 GB and generating roughly 227 tokens per second. The fit is tight.

Nemotron 3-Nano-30B-A3B— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q4_K_M, using about 18.1 GB and generating roughly 230 tokens per second. The fit is tight.

Nemotron 3-Nano-30B-A3B— 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-Nano-30B-A3B— how many parameters does it have?

It has a parameter count of 31.6B. "Nano 30B-A3B Base contains 31.6B total parameters out of which 3.2B are activ". 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-Nano-30B-A3B— who created it?

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

Source

Original publication

Record last updated 8 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.

All AI models