BERT-Large TPS calculator

Open weights Google 340M parameters October 2018

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 · 108 tok/s

Fastest card

B200

9,965 tok/s · 180 GB

Which GPUs can run BERT-Large?

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
9,965 tok/s 5,979–15,945 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.1 GB	Q8_0	Comfortable
9,965 tok/s 5,979–15,945 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.1 GB	Q8_0	Comfortable
7,958 tok/s 4,775–12,732 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.1 GB	Q8_0	Comfortable
7,958 tok/s 4,775–12,732 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.1 GB	Q8_0	Comfortable
6,364 tok/s 3,818–10,183 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
6,091 tok/s 3,655–9,746 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.1 GB	Q8_0	Comfortable
6,091 tok/s 3,655–9,746 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.1 GB	Q8_0	Comfortable
5,830 tok/s 3,498–9,328 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.1 GB	Q8_0	Comfortable
5,174 tok/s 3,104–8,278 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
5,174 tok/s 3,104–8,278 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
5,174 tok/s 3,104–8,278 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
4,908 tok/s 2,945–7,853 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,185 tok/s 2,511–6,697 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,185 tok/s 2,511–6,697 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.1 GB	Q8_0	Comfortable
4,185 tok/s 2,511–6,697 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,185 tok/s 2,511–6,697 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,185 tok/s 2,511–6,697 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
3,187 tok/s 1,912–5,099 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.1 GB	Q8_0	Comfortable
3,187 tok/s 1,912–5,099 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.1 GB	Q8_0	Comfortable
2,656 tok/s 1,593–4,249 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
2,599 tok/s 1,559–4,159 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.1 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.1 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.1 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.1 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: Google
Organisation type: Industry
Country: United States of America
Published: 11 October 2018
Authors: J Devlin, MW Chang, K Lee, K Toutanova

What it does

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

Domain: Language
Task: Question answering, Text autocompletion
Approach: Self-supervised learning

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: 340M
Training data: 2,649,900,000 tokens
Epochs: 40
Batch size: 128,000

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: 2.9 × 10²⁰ FLOP
How it was established: Operation counting,Hardware,Third-party estimation

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: 64
Chip-hours: 6,144
Wall-clock time: 96 hours
Hardware utilisation: MFU 28.0%
Power draw: 37.0 kW
Compute cost: $1,751

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: Open source

How it is classified

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

Why it is tracked: Highly cited
Record confidence: Confident
Citations: 114,811

Sources

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

Reference: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run BERT-Large

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 BERT-Large

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

Tesla C1080

Memory needed

1.1 GB

Fastest

9,965 tok/s

BERT-Large is small enough at 340M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 108 tokens per second.

A B200 is the fastest we calculate for it: about 9,965 tokens per second, from 8,000 GB/s of memory bandwidth.

What this model is

BERT-Large was published by Google, in United States of America, in October 2018. It comes out of industry.

It works in Language, and is recorded as doing question answering, Text autocompletion.

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.

What decides the speed

Across every card that can run it, the middle of the range is about 279.8 tokens per second, and 818 of them clear the ten tokens per second that roughly matches reading speed.

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

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.

Training and provenance

Producing it required around 2.9 × 10²⁰ FLOP of arithmetic, on Google TPU v2, which is a statement about the training budget rather than about inference.

The training set ran to roughly 2,649,900,000 tokens.

Its inclusion criterion is highly cited.

Step by step

How to choose a GPU for BERT-Large

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

Look at what BERT-Large actually needs — around 1.1 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
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 BERT-Large can slip off a card that handles short questions easily.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy of BERT-Large — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

The speed ordering for BERT-Large is effectively an ordering by memory bandwidth, which is why the B200 tops it at 9,965 tok/s.
05

Check the fit verdict before buying

Tight means BERT-Large 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 BERT-Large alone — a card is usually bought for more than one model.

Answers

BERT-Large — common questions

How many parameters does BERT-Large have?

BERT-Large has 340M parameters. 340M. 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 BERT-Large?

BERT-Large was published by Google, based in United States of America, categorised as industry.

When was BERT-Large released?

BERT-Large was published in October 2018. 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 BERT-Large used for?

BERT-Large works in Language, and is recorded as handling question answering, Text autocompletion. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download BERT-Large?

The weights for BERT-Large 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 BERT-Large?

Around 2.9 × 10²⁰ 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 BERT-Large if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down. Our figures for BERT-Large assume it is fully resident.

Would two GPUs run BERT-Large faster?

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

Why does the quantisation differ between cards for BERT-Large?

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

How accurate are these BERT-Large speed estimates?

These are estimates with real error bars. The fastest result here, 5,979–15,945 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run BERT-Large?

The smallest card in our catalogue that holds BERT-Large is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.1 GB, and produces roughly 108 tokens per second. 818 cards in total can run it.

How fast is BERT-Large on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 9,965 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 BERT-Large clear that.

How much VRAM does BERT-Large need?

About 1.1 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 BERT-Large on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,856 tokens per second — a comfortable fit.

Can I run BERT-Large on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,137 tokens per second — a comfortable fit.

Can I run BERT-Large on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,408 tokens per second — a comfortable fit.

Can I run BERT-Large on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.1 GB and generating roughly 1,669 tokens per second — a comfortable fit.

Is BERT-Large open source?

Its weights are published, so BERT-Large 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.

Source

Original publication

Record last updated 25 May 2026

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