Nemotron-4 340B TPS calculator

Open weights NVIDIA 340B parameters June 2024

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

6 of 818 cards that can run it

Smallest card that fits

Radeon Instinct MI300X

192 GB · Q3_K_M · 14.0 tok/s

Fastest card

B300

17.8 tok/s · 288 GB

Which GPUs can run Nemotron-4 340B?

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

6 cards match

Calculating

					Needs	Quantisation	Fit
17.8 tok/s 11–28 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	246.0 GB	Q5_K_M	Tight
14.2 tok/s 9–23 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	246.0 GB	Q5_K_M	Tight
14.2 tok/s 9–23 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	246.0 GB	Q5_K_M	Tight
14.0 tok/s 8–22 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	166.8 GB	Q3_K_M	Tight
14.0 tok/s 8–22 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	166.8 GB	Q3_K_M	Tight
13.5 tok/s 8–22 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	206.4 GB	Q4_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: 14 June 2024
Authors: Bo Adler, Niket Agarwal, Ashwath Aithal, Dong H. Anh, Pallab Bhattacharya, Annika Brundyn, Jared Casper, Bryan Catanzaro, Sharon Clay, Jonathan Cohen, Sirshak Das, Ayush Dattagupta, Olivier Delalleau, Leon Derczynski, Yi Dong, Daniel Egert, Ellie Evans, Aleksander Ficek, Denys Fridman, Shaona Ghosh, Boris Ginsburg, Igor Gitman, Tomasz Grzegorzek, Robert Hero, Jining Huang, Vibhu Jawa, Joseph Jenni…

What it does

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

Domain: Language
Task: Language modeling/generation, Chat, Question answering
Numerical format: BF16

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: 340B
Training data: 9,000,000,000,000 tokens
Batch size: 9,437,184

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 × 10²⁵ 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 H100 SXM5 80GB
Chips used: 6,144
Wall-clock time: 2,200 hours (91.7 days)
Hardware utilisation: MFU 41.1%
Power draw: 8.5 MW
Compute cost: $21,271,018

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)
Training code: Unreleased
Hugging Face: nvidia

How it is classified

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

Frontier model: Yes
Likely above 10²³ FLOP: Yes
Why it is tracked: Training cost
Record confidence: Confident

Sources

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

Reference: NVIDIA Releases Open Synthetic Data Generation Pipeline for Training Large Language Models
Last updated: 18 December 2025

The extremes

The ten fastest GPUs for Nemotron-4 340B

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-4 340B

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

Radeon Instinct MI300X

Memory needed

166.8 GB

Fastest

17.8 tok/s

At 340B parameters, Nemotron-4 340B is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 6 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 Radeon Instinct MI300X with 192 GB, running it at Q3_K_M and producing around 14.0 tokens per second.

A B300 is the fastest we calculate for it: about 17.8 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

Nemotron-4 340B was published by NVIDIA, in United States of America, in June 2024. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Chat, Question answering.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the nvidia organisation on Hugging Face.

What decides the speed

Half the cards that hold it manage more than 14.1 tokens per second, and 6 exceed reading speed outright.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

Training and provenance

The training run consumed about 1.8 × 10²⁵ FLOP, on NVIDIA H100 SXM5 80GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 9,000,000,000,000 tokens of text.

Its inclusion criterion is training cost.

Step by step

How to choose a GPU for Nemotron-4 340B

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-4 340B — around 166.8 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Nemotron-4 340B stops fitting a card that seemed fine.
03

Set a quality floor

Compression is what makes Nemotron-4 340B 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

The speed ordering for Nemotron-4 340B is effectively an ordering by memory bandwidth, which is why the B300 tops it at 17.8 tok/s.
05

Look at the headroom, not just the fit

A tight fit runs Nemotron-4 340B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Open the card you have settled on

Following a card through to its own page shows every other model it can hold, which is the question that follows once Nemotron-4 340B is settled.

Answers

Nemotron-4 340B — common questions

Can I run Nemotron-4 340B if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded Nemotron-4 340B is rarely worth using — the nearest miss we calculate is short by 44.4 GB. Every figure here assumes the whole model is on the card.

Would two GPUs run Nemotron-4 340B faster?

Capacity adds across cards; throughput does not. Since 6 of the cards we track already hold Nemotron-4 340B on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Nemotron-4 340B?

Each card is shown running the least-compressed copy it can hold, and Nemotron-4 340B appears at 3 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Nemotron-4 340B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 11–28 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-4 340B?

The smallest card in our catalogue that holds Nemotron-4 340B is the Radeon Instinct MI300X, with 192 GB of memory. It runs the model at Q3_K_M using about 166.8 GB, and produces roughly 14.0 tokens per second. 6 cards in total can run it.

How fast is Nemotron-4 340B on a GPU?

It depends on the card. The quickest we calculate is a B300 at about 17.8 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 6 of the cards that can run Nemotron-4 340B clear that.

How much VRAM does Nemotron-4 340B need?

About 166.8 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-4 340B open source?

Its weights are published, so Nemotron-4 340B 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-4 340B have?

Nemotron-4 340B has 340B parameters. 340B. 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-4 340B?

Nemotron-4 340B was published by NVIDIA, based in United States of America, categorised as industry.

When was Nemotron-4 340B released?

Nemotron-4 340B was published in June 2024. 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-4 340B used for?

Nemotron-4 340B works in Language, and is recorded as handling language modeling/generation, Chat, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Nemotron-4 340B?

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

How much compute was used to train Nemotron-4 340B?

Around 1.8 × 10²⁵ FLOP, on 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.

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