Nemotron-3-8B TPS calculator

Open weights NVIDIA 8B parameters November 2023

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

582 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Quadro 6000

6 GB · IQ4_XS · 15.9 tok/s

Fastest card

B200

424 tok/s · 180 GB

Which GPUs can run Nemotron-3-8B?

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

582 cards match

Calculating

					Needs	Quantisation	Fit
424 tok/s 254–678 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	9.3 GB	Q8_0	Comfortable
424 tok/s 254–678 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	9.3 GB	Q8_0	Comfortable
338 tok/s 203–541 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	9.3 GB	Q8_0	Comfortable
338 tok/s 203–541 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	9.3 GB	Q8_0	Comfortable
270 tok/s 162–433 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	9.3 GB	Q8_0	Comfortable
259 tok/s 155–414 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.3 GB	Q8_0	Comfortable
259 tok/s 155–414 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.3 GB	Q8_0	Comfortable
248 tok/s 149–396 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	9.3 GB	Q8_0	Comfortable
220 tok/s 132–352 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	9.3 GB	Q8_0	Comfortable
220 tok/s 132–352 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	9.3 GB	Q8_0	Comfortable
220 tok/s 132–352 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	9.3 GB	Q8_0	Comfortable
209 tok/s 125–334 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
178 tok/s 107–285 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	9.3 GB	Q8_0	Comfortable
141 tok/s 85–225 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.5 GB	Q5_K_M	Tight
135 tok/s 81–217 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	9.3 GB	Q8_0	Comfortable
135 tok/s 81–217 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	9.3 GB	Q8_0	Comfortable
120 tok/s 72–192 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	7.4 GB	Q6_K	Comfortable
113 tok/s 68–181 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	9.3 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	9.3 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	9.3 GB	Q8_0	Comfortable
108 tok/s 65–173 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	9.3 GB	Q8_0	Comfortable

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 November 2023

What it does

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

Domain: Language
Task: Chat, Language generation, Language modeling/generation, Translation, Code generation, Question answering

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: 8B
Training data: 3,800,000,000,000 tokens
Batch size: 25,667,824

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: 1.8 × 10²³ FLOP
How it was established: Operation counting,Hardware

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 A100
Chips used: 1,024
Wall-clock time: 456 hours (19 days)
Hardware utilisation: MFU 34.7%
Power draw: 812.5 kW
Compute cost: $214,467

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)
Training code: Unreleased

How it is classified

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

Likely above 10²³ FLOP: Yes
Why it is tracked: SOTA improvement
Record confidence: Confident

Sources

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

Reference: NVIDIA AI Foundation Models: Build Custom Enterprise Chatbots and Co-Pilots with Production-Ready LLMs
Last updated: 18 December 2025

The extremes

The ten fastest GPUs that run Nemotron-3-8B

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-3-8B

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

The hardware side

Minimum card

Quadro 6000

Memory needed

5.1 GB

Fastest

424 tok/s

Nemotron-3-8B is small enough at 8B parameters that hardware is rarely the obstacle — 582 of the cards we track can run it, including cards several years old.

At the low end, a Quadro 6000 handles it — 6 GB, at IQ4_XS, for about 15.9 tokens per second.

At the other end, a B200 generates roughly 424 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

Nemotron-3-8B was published by NVIDIA, in United States of America, in November 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing chat, Language generation, Language modeling/generation, Translation, Code generation, Question answering.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

Understanding the speeds

Across every card that can run it, the middle of the range is about 23.8 tokens per second, and 551 of them clear the ten tokens per second that roughly matches reading speed.

It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.

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.

How it was trained

Producing it required around 1.8 × 10²³ FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.

It was trained on about 3,800,000,000,000 tokens of text.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Step by step

How to choose a GPU for Nemotron-3-8B

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-3-8B actually needs — around 5.1 GB at IQ4_XS. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Nemotron-3-8B.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of Nemotron-3-8B — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for Nemotron-3-8B follows memory bandwidth, not core counts, which is why the B200 tops it at 424 tok/s.
05

Check the fit verdict before buying

Tight means Nemotron-3-8B loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
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-3-8B alone — a card is usually bought for more than one model.

Answers

Nemotron-3-8B — common questions

What GPU do I need to run Nemotron-3-8B?

The smallest card in our catalogue that holds Nemotron-3-8B is the Quadro 6000, with 6 GB of memory. It runs the model at IQ4_XS using about 5.1 GB, and produces roughly 15.9 tokens per second. 582 cards in total can run it.

How fast is Nemotron-3-8B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 424 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 551 of the cards that can run Nemotron-3-8B clear that.

How much VRAM does Nemotron-3-8B need?

About 5.1 GB at IQ4_XS 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.

Can I run Nemotron-3-8B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q5_K_M, using about 6.5 GB and generating roughly 141 tokens per second — a tight fit.

Can I run Nemotron-3-8B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 9.3 GB and generating roughly 48.3 tokens per second — a tight fit.

Can I run Nemotron-3-8B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 9.3 GB and generating roughly 59.8 tokens per second — a comfortable fit.

Can I run Nemotron-3-8B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 9.3 GB and generating roughly 70.9 tokens per second — a comfortable fit.

Is Nemotron-3-8B open source?

Its weights are published, so Nemotron-3-8B 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-3-8B have?

Nemotron-3-8B has 8B parameters. 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-3-8B?

Nemotron-3-8B was published by NVIDIA, based in United States of America, categorised as industry.

When was Nemotron-3-8B released?

Nemotron-3-8B was published in November 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

What is Nemotron-3-8B used for?

Nemotron-3-8B works in Language, and is recorded as handling chat, Language generation, Language modeling/generation, Translation, Code generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Nemotron-3-8B?

The weights for Nemotron-3-8B 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-3-8B?

Around 1.8 × 10²³ FLOP, on NVIDIA A100. 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-3-8B if it does not fit in my GPU?

It can be split between the card and system memory, but Nemotron-3-8B generates painfully slowly that way — the nearest miss we calculate is short by 1.0 GB. Nothing on this page assumes offloading.

Would two GPUs run Nemotron-3-8B faster?

Two cards buy memory rather than speed. That matters for Nemotron-3-8B only if one card cannot hold it — 582 can, so a second adds little.

Why does the quantisation differ between cards for Nemotron-3-8B?

A larger card holds a more accurate copy. Across the cards that run Nemotron-3-8B, 4 compression levels are used; the floor control above pins it to one.

How accurate are these Nemotron-3-8B speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 254–678 tok/s on the B200 rather than a single number.

Source

Original publication

Record last updated 18 December 2025

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