AraBERT TPS calculator

Open weights American University of Beirut 110M parameters March 2020

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 · 335 tok/s

Fastest card

B200

30,802 tok/s · 180 GB

Which GPUs can run AraBERT?

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
30,802 tok/s 18,481–49,283 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.8 GB	Q8_0	Comfortable
30,802 tok/s 18,481–49,283 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.8 GB	Q8_0	Comfortable
24,596 tok/s 14,758–39,354 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.8 GB	Q8_0	Comfortable
24,596 tok/s 14,758–39,354 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.8 GB	Q8_0	Comfortable
19,671 tok/s 11,803–31,474 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
18,828 tok/s 11,297–30,124 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.8 GB	Q8_0	Comfortable
18,828 tok/s 11,297–30,124 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.8 GB	Q8_0	Comfortable
18,019 tok/s 10,812–28,831 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.8 GB	Q8_0	Comfortable
15,992 tok/s 9,595–25,587 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
15,992 tok/s 9,595–25,587 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
15,992 tok/s 9,595–25,587 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
15,170 tok/s 9,102–24,272 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
12,937 tok/s 7,762–20,699 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
12,937 tok/s 7,762–20,699 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.8 GB	Q8_0	Comfortable
12,937 tok/s 7,762–20,699 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
12,937 tok/s 7,762–20,699 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
12,937 tok/s 7,762–20,699 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
9,851 tok/s 5,910–15,761 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.8 GB	Q8_0	Comfortable
9,851 tok/s 5,910–15,761 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.8 GB	Q8_0	Comfortable
8,209 tok/s 4,925–13,134 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
8,034 tok/s 4,820–12,854 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
7,855 tok/s 4,713–12,567 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.8 GB	Q8_0	Comfortable
7,855 tok/s 4,713–12,567 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.8 GB	Q8_0	Comfortable
7,855 tok/s 4,713–12,567 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.8 GB	Q8_0	Comfortable
7,855 tok/s 4,713–12,567 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.8 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: American University of Beirut
Organisation type: Academia
Country: Lebanon
Published: 30 March 2020
Authors: Wissam Antoun, Fady Baly, Hazem Hajj

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

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: 110M
Training data: tokens
Epochs: 27

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: 3.2 × 10¹⁹ 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: Google TPU v2
Chips used: 8
Wall-clock time: 96 hours
Power draw: 4.6 kW

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)
Hugging Face: aubmindlab

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: AraBERT: Transformer-based Model for Arabic Language Understanding
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run AraBERT

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 AraBERT

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

Tesla C1080

Memory needed

0.8 GB

Fastest

30,802 tok/s

AraBERT is small enough at 110M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 335 tokens per second.

The quickest result comes from a B200 at around 30,802 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

About this model

AraBERT was published by American University of Beirut, in Lebanon, in March 2020. academia is the category the publisher falls under.

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

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. It is published under the aubmindlab organisation on Hugging Face.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 864.9 tokens per second, and 818 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.

Training and provenance

The training run consumed about 3.2 × 10¹⁹ FLOP, on Google TPU v2. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Step by step

How to choose a GPU for AraBERT

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

Every card here has been checked against AraBERT — around 0.8 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context AraBERT can slip off a card that handles short questions easily.
03

Set a quality floor

Compression is what makes AraBERT fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Sort by speed

Ranking by tokens per second for AraBERT follows memory bandwidth, not core counts, which is why the B200 tops it at 30,802 tok/s.
05

Look at the headroom, not just the fit

Tight means AraBERT 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 AraBERT is settled.

Answers

AraBERT — common questions

Where can I download AraBERT?

Its weights are published under the aubmindlab 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 AraBERT?

Around 3.2 × 10¹⁹ FLOP, on Google TPU v2. 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 AraBERT if it does not fit in my GPU?

It can be split between the card and system memory, but AraBERT generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run AraBERT faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold AraBERT on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for AraBERT?

Because capacity varies, so does how hard AraBERT has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these AraBERT 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 18,481–49,283 tok/s on the B200 rather than a single number.

What GPU do I need to run AraBERT?

The smallest card in our catalogue that holds AraBERT is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.8 GB, and produces roughly 335 tokens per second. 818 cards in total can run it.

How fast is AraBERT on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 30,802 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 818 of the cards that can run AraBERT clear that.

How much VRAM does AraBERT need?

About 0.8 GB at Q8_0 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 AraBERT on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.8 GB and generating roughly 5,737 tokens per second — a comfortable fit.

Can I run AraBERT on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.8 GB and generating roughly 3,513 tokens per second — a comfortable fit.

Can I run AraBERT on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.8 GB and generating roughly 4,351 tokens per second — a comfortable fit.

Can I run AraBERT on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.8 GB and generating roughly 5,159 tokens per second — a comfortable fit.

Is AraBERT open source?

Its weights are published, so AraBERT 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 AraBERT have?

AraBERT has 110M parameters. We use the BERTbase configuration that has 12 encoder blocks, 768 hidden dimensions, 12 attention heads, 512 maximum sequence length, and a total of ∼110M 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 AraBERT?

AraBERT was published by American University of Beirut, based in Lebanon, categorised as academia.

When was AraBERT released?

AraBERT was published in March 2020. 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 AraBERT used for?

AraBERT works in Language, and is recorded as handling language modeling/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.

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