EXAONE 3.0 TPS calculator

Open weights LG AI Research 7.8B parameters August 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

582 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Quadro 6000

6 GB · IQ4_XS · 16.2 tok/s

Fastest card

B200

433 tok/s · 180 GB

Which GPUs can run EXAONE 3.0?

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
433 tok/s 260–693 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	9.1 GB	Q8_0	Comfortable
433 tok/s 260–693 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	9.1 GB	Q8_0	Comfortable
346 tok/s 208–554 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	9.1 GB	Q8_0	Comfortable
346 tok/s 208–554 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	9.1 GB	Q8_0	Comfortable
277 tok/s 166–443 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	9.1 GB	Q8_0	Comfortable
265 tok/s 159–424 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.1 GB	Q8_0	Comfortable
265 tok/s 159–424 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	9.1 GB	Q8_0	Comfortable
253 tok/s 152–406 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	9.1 GB	Q8_0	Comfortable
225 tok/s 135–360 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	9.1 GB	Q8_0	Comfortable
225 tok/s 135–360 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	9.1 GB	Q8_0	Comfortable
225 tok/s 135–360 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	9.1 GB	Q8_0	Comfortable
213 tok/s 128–341 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	9.1 GB	Q8_0	Comfortable
182 tok/s 109–291 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.1 GB	Q8_0	Comfortable
182 tok/s 109–291 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	9.1 GB	Q8_0	Comfortable
182 tok/s 109–291 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	9.1 GB	Q8_0	Comfortable
182 tok/s 109–291 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	9.1 GB	Q8_0	Comfortable
182 tok/s 109–291 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	9.1 GB	Q8_0	Comfortable
144 tok/s 86–231 · low confidence	CMP 170HX 8 GB NVIDIA	8 GB	1,490 GB/s	Sep 2021	6.3 GB	Q5_K_M	Tight
139 tok/s 83–222 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	9.1 GB	Q8_0	Comfortable
139 tok/s 83–222 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	9.1 GB	Q8_0	Comfortable
123 tok/s 74–196 · low confidence	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	7.3 GB	Q6_K	Comfortable
115 tok/s 69–185 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	9.1 GB	Q8_0	Comfortable
113 tok/s 68–181 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	9.1 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	9.1 GB	Q8_0	Comfortable
110 tok/s 66–177 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	9.1 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: LG AI Research
Organisation type: Industry
Country: Korea (Republic of)
Published: 7 August 2024
Authors: LG AI Research: Soyoung An, Kyunghoon Bae, Eunbi Choi, Stanley Jungkyu Choi, Yemuk Choi, Seokhee Hong, Yeonjung Hong, Junwon Hwang, Hyojin Jeon, Gerrard Jeongwon Jo, Hyunjik Jo, Jiyeon Jung, Yountae Jung, Euisoon Kim, Hyosang Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Youchul Kim, Edward Hwayoung Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Lee, Moontae Lee, Seung…

What it does

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

Domain: Language
Task: Language modeling/generation, 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: 7.8B
Training data: 8,000,000,000,000 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 × 10²³ FLOP
How it was established: Reported,Operation counting

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 (non-commercial)
Training code: Unreleased
Hugging Face: LGAI-EXAONE

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
Record confidence: Confident

Sources

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

Reference: EXAONE 3.0 7.8B Instruction Tuned Language Model
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run EXAONE 3.0

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 EXAONE 3.0

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

Quadro 6000

Memory needed

5.0 GB

Fastest

433 tok/s

EXAONE 3.0 is small enough at 7.8B parameters that hardware is rarely the obstacle — 582 of the cards we track can run it, including cards several years old.

The least hardware that works is a Quadro 6000. Its 6 GB is enough at IQ4_XS compression, giving roughly 16.2 tokens per second.

At the other end, a B200 generates roughly 433 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

What this model is

EXAONE 3.0 was published by LG AI Research, in Korea (Republic of), in August 2024. The organisation is categorised as industry.

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

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the LGAI-EXAONE organisation on Hugging Face.

What decides the speed

Half the cards that hold it manage more than 24.3 tokens per second, and 551 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.

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 4 × 10²³ 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 8,000,000,000,000 tokens of text.

Step by step

How to choose a GPU for EXAONE 3.0

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

01

Read the memory figure first

Look at what EXAONE 3.0 actually needs — around 5.0 GB at IQ4_XS. 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 EXAONE 3.0 stops fitting a card that seemed fine.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of EXAONE 3.0 — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

Sort by speed to see how cards rank for EXAONE 3.0. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 433 tok/s.
05

Check the fit verdict before buying

Tight means EXAONE 3.0 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

See what else that card runs

Following a card through to its own page shows every other model it can hold, which is the question that follows once EXAONE 3.0 is settled.

Answers

EXAONE 3.0 — common questions

How much compute was used to train EXAONE 3.0?

Around 4 × 10²³ 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.

Can I run EXAONE 3.0 if it does not fit in my GPU?

It can be split between the card and system memory, but EXAONE 3.0 generates painfully slowly that way — the nearest miss we calculate is short by 0.9 GB. Nothing on this page assumes offloading.

Would two GPUs run EXAONE 3.0 faster?

A second card roughly doubles the memory available but not the generation rate. With 582 cards already able to run EXAONE 3.0 alone, the case for pairing is weak.

Why does the quantisation differ between cards for EXAONE 3.0?

A larger card holds a more accurate copy. Across the cards that run EXAONE 3.0, 4 compression levels are used; the floor control above pins it to one.

How accurate are these EXAONE 3.0 speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 260–693 tok/s on the B200, 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 EXAONE 3.0?

The smallest card in our catalogue that holds EXAONE 3.0 is the Quadro 6000, with 6 GB of memory. It runs the model at IQ4_XS using about 5.0 GB, and produces roughly 16.2 tokens per second. 582 cards in total can run it.

How fast is EXAONE 3.0 on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 433 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 EXAONE 3.0 clear that.

How much VRAM does EXAONE 3.0 need?

About 5.0 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 EXAONE 3.0 on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q5_K_M, using about 6.3 GB and generating roughly 144 tokens per second — a tight fit.

Can I run EXAONE 3.0 on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 9.1 GB and generating roughly 49.4 tokens per second — a tight fit.

Can I run EXAONE 3.0 on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 9.1 GB and generating roughly 61.2 tokens per second — a comfortable fit.

Can I run EXAONE 3.0 on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 9.1 GB and generating roughly 72.6 tokens per second — a comfortable fit.

Is EXAONE 3.0 open source?

Its weights are published, so EXAONE 3.0 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 EXAONE 3.0 have?

EXAONE 3.0 has 7.8B parameters. 7.8B. 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 EXAONE 3.0?

EXAONE 3.0 was published by LG AI Research, based in Korea (Republic of), categorised as industry.

When was EXAONE 3.0 released?

EXAONE 3.0 was published in August 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 EXAONE 3.0 used for?

EXAONE 3.0 works in Language, and is recorded as handling language modeling/generation, Code generation, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Where can I download EXAONE 3.0?

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

Source

Original publication

Record last updated 28 November 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