EXAONE Deep 2.4B TPS calculator

Open weights LG AI Research 2.4B parameters March 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 15.4 tok/s

Fastest card

B200

1,412 tok/s · 180 GB

Which GPUs can run EXAONE Deep 2.4B?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
1,412 tok/s 847–2,259 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.3 GB	Q8_0	Comfortable
1,412 tok/s 847–2,259 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.3 GB	Q8_0	Comfortable
1,127 tok/s 676–1,804 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.3 GB	Q8_0	Comfortable
1,127 tok/s 676–1,804 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.3 GB	Q8_0	Comfortable
902 tok/s 541–1,443 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.3 GB	Q8_0	Comfortable
863 tok/s 518–1,381 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.3 GB	Q8_0	Comfortable
863 tok/s 518–1,381 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.3 GB	Q8_0	Comfortable
826 tok/s 496–1,321 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.3 GB	Q8_0	Comfortable
733 tok/s 440–1,173 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.3 GB	Q8_0	Comfortable
733 tok/s 440–1,173 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.3 GB	Q8_0	Comfortable
733 tok/s 440–1,173 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.3 GB	Q8_0	Comfortable
695 tok/s 417–1,112 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
593 tok/s 356–949 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
593 tok/s 356–949 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.3 GB	Q8_0	Comfortable
593 tok/s 356–949 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
593 tok/s 356–949 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
593 tok/s 356–949 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.3 GB	Q8_0	Comfortable
451 tok/s 271–722 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.3 GB	Q8_0	Comfortable
451 tok/s 271–722 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.3 GB	Q8_0	Comfortable
376 tok/s 226–602 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.3 GB	Q8_0	Comfortable
368 tok/s 221–589 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.3 GB	Q8_0	Comfortable
360 tok/s 216–576 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.3 GB	Q8_0	Comfortable
360 tok/s 216–576 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.3 GB	Q8_0	Comfortable
360 tok/s 216–576 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.3 GB	Q8_0	Comfortable
360 tok/s 216–576 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.3 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: LG AI Research
Organisation type: Industry
Country: Korea (Republic of)
Published: 16 March 2025
Authors: LG AI Research, Kyunghoon Bae, Eunbi Choi, Kibong Choi, Stanley Jungkyu Choi, Yemuk Choi, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Kijeong Jeon, Gerrard Jeongwon Jo, Hyunjik Jo, Jiyeon Jung, Hyosang Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Youchul Kim, Edward Hwayoung Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Lee, Sangha Park, Yongmin Park, Sihoon…

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, Quantitative reasoning, Code generation
Base model: EXAONE 3.5 2.4B

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: 2.4B
Training data: 12,000,000,000 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: 9.4 × 10²² FLOP
How it was established: Reported,Operation counting
Fine-tuning compute: 5.3 × 10²⁰ 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
Cloud vendor: Google Cloud

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.

Record confidence: Confident

Sources

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

Reference: EXAONE Deep: LLMs with Enhanced Reasoning Performance
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run EXAONE Deep 2.4B

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 Deep 2.4B

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

Tesla C1080

Memory needed

3.3 GB

Fastest

1,412 tok/s

EXAONE Deep 2.4B reaches a parameter count of 2.4B. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 818.

At the low end it is handled by Tesla C1080, with a memory capacity of 4 GB, running it at a compression of Q8_0 and producing around 15.4 tokens per second.

Top of the range is B200, generating roughly 1,412 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Where it came from

EXAONE Deep 2.4B was published by LG AI Research, in the country recorded as Korea (Republic of), during March 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, Question answering, Quantitative reasoning, Code generation.

It builds on EXAONE 3.5 2.4B. Most models at this scale are adapted from an existing base rather than built from nothing.

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. On Hugging Face it is published under the organisation LGAI-EXAONE.

Understanding the speeds

The median result is around 39.6 tokens per second. Clearing the ten tokens per second that roughly matches reading speed: 783 of them.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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 9.4 × 10²² 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.

Training consumed a corpus of around 12,000,000,000 tokens of text.

Step by step

How to choose a GPU for EXAONE Deep 2.4B

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

Start from what it actually needs, which is the requirement of EXAONE Deep 2.4B, needing around 3.3 GB at a compression of Q8_0. No amount of processing power compensates for a card that cannot hold it.
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 a card that seemed fine stops fitting EXAONE Deep 2.4B.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold, reaching a compression of Q8_0 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

Compare tokens per second, not specifications

Sort by speed to see how cards rank for EXAONE Deep 2.4B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 1,412 tok/s.
05

Check the fit verdict before buying

Tight means it loads and works with no room to raise the context later, in the case of EXAONE Deep 2.4B. 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

Open the card you have settled on

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 EXAONE Deep 2.4B.

Answers

EXAONE Deep 2.4B — common questions

EXAONE Deep 2.4B— how much VRAM does it need?

It needs about 3.3 GB at a compression of Q8_0, 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.

EXAONE Deep 2.4B— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q8_0, using about 3.3 GB and generating roughly 263 tokens per second. The fit is comfortable.

EXAONE Deep 2.4B— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q8_0, using about 3.3 GB and generating roughly 161 tokens per second. The fit is comfortable.

EXAONE Deep 2.4B— 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 Q8_0, using about 3.3 GB and generating roughly 199 tokens per second. The fit is comfortable.

EXAONE Deep 2.4B— 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 Q8_0, using about 3.3 GB and generating roughly 236 tokens per second. The fit is comfortable.

EXAONE Deep 2.4B— 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.

EXAONE Deep 2.4B— how many parameters does it have?

It has a parameter count of 2.4B. 2.4B. 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.

EXAONE Deep 2.4B— who created it?

It was published by LG AI Research, based in Korea (Republic of), an organisation categorised as industry.

EXAONE Deep 2.4B— when was it released?

It was published in March 2025.

EXAONE Deep 2.4B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Question answering, Quantitative reasoning, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

EXAONE Deep 2.4B— where can I download it?

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

EXAONE Deep 2.4B— how much compute was used to train it?

Training consumed around 9.4 × 10²² 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.

EXAONE Deep 2.4B— 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. Every figure here assumes the whole model is resident on the card.

EXAONE Deep 2.4B— 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: 818. So a second card is rarely the answer here.

EXAONE Deep 2.4B— 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: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

EXAONE Deep 2.4B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 847–2,259 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

EXAONE Deep 2.4B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla C1080, with a memory capacity of 4 GB. It runs the model at a compression of Q8_0 using about 3.3 GB, and produces roughly 15.4 tokens per second. The number of cards able to run it in total: 818.

EXAONE Deep 2.4B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 1,412 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: 783.

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