CamemBERT TPS calculator

Open weights Facebook,INRIA,Sorbonne University 335M parameters November 2019

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 · 110 tok/s

Fastest card

B200

10,114 tok/s · 180 GB

Which GPUs can run CamemBERT?

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
10,114 tok/s 6,068–16,183 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.1 GB	Q8_0	Comfortable
10,114 tok/s 6,068–16,183 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.1 GB	Q8_0	Comfortable
8,076 tok/s 4,846–12,922 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.1 GB	Q8_0	Comfortable
8,076 tok/s 4,846–12,922 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.1 GB	Q8_0	Comfortable
6,459 tok/s 3,875–10,335 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
6,182 tok/s 3,709–9,892 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.1 GB	Q8_0	Comfortable
6,182 tok/s 3,709–9,892 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.1 GB	Q8_0	Comfortable
5,917 tok/s 3,550–9,467 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.1 GB	Q8_0	Comfortable
5,251 tok/s 3,151–8,402 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
5,251 tok/s 3,151–8,402 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
5,251 tok/s 3,151–8,402 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.1 GB	Q8_0	Comfortable
4,981 tok/s 2,989–7,970 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
4,248 tok/s 2,549–6,797 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.1 GB	Q8_0	Comfortable
3,235 tok/s 1,941–5,175 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.1 GB	Q8_0	Comfortable
3,235 tok/s 1,941–5,175 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.1 GB	Q8_0	Comfortable
2,695 tok/s 1,617–4,313 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
2,638 tok/s 1,583–4,221 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.1 GB	Q8_0	Comfortable
2,579 tok/s 1,547–4,127 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.1 GB	Q8_0	Comfortable
2,579 tok/s 1,547–4,127 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.1 GB	Q8_0	Comfortable
2,579 tok/s 1,547–4,127 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.1 GB	Q8_0	Comfortable
2,579 tok/s 1,547–4,127 · 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: Facebook,INRIA,Sorbonne University
Organisation type: Industry,Academia,Academia
Country: United States of America, France
Published: 10 November 2019
Authors: Louis Martin, Benjamin Muller, Pedro Javier Ortiz Suárez, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah, Benoît Sagot

What it does

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

Domain: Language
Task: Language modeling/generation, Part-of-speech tagging, Named entity recognition (NER)

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: 335M
Training data: 28,615,771,780 tokens
Epochs: 13

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: 8.3 × 10²⁰ FLOP
How it was established: Hardware,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 V100
Wall-clock time: 24 hours
Compute cost: $2,320

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

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: SOTA improvement
Record confidence: Confident
Citations: 1,083

Sources

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

Reference: CamemBERT: a Tasty French Language Model
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run CamemBERT

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 CamemBERT

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

1.1 GB

Fastest

10,114 tok/s

CamemBERT is small enough at 335M 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 110 tokens per second.

A B200 is the fastest we calculate for it: about 10,114 tokens per second, from 8,000 GB/s of memory bandwidth.

About this model

CamemBERT was published by Facebook,INRIA,Sorbonne University, in United States of America, in November 2019. It comes out of industry,Academia,Academia.

It works in Language, and is recorded as doing language modeling/generation, Part-of-speech tagging, Named entity recognition (NER).

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

How fast it runs, and why

The median result is around 284.0 tokens per second; 818 cards produce text faster than most people read it.

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.

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.

What went into building it

The training run consumed about 8.3 × 10²⁰ FLOP, on NVIDIA V100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 28,615,771,780 tokens of text.

Its inclusion criterion is sOTA improvement.

Step by step

How to choose a GPU for CamemBERT

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

The table lists every card that can hold CamemBERT — around 1.1 GB at Q8_0. That figure, not the card's headline performance, is what decides whether it runs.
02

Match the context to your actual use

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

Set a quality floor

Compression is what makes CamemBERT 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

Compare tokens per second, not specifications

Ranking by tokens per second for CamemBERT follows memory bandwidth, not core counts, which is why the B200 tops it at 10,114 tok/s.
05

Check the fit verdict before buying

Tight means CamemBERT 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 CamemBERT is settled.

Answers

CamemBERT — common questions

How many parameters does CamemBERT have?

CamemBERT has 335M parameters. CamemBERT Large, Table 4. 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 CamemBERT?

CamemBERT was published by Facebook,INRIA,Sorbonne University, based in United States of America, categorised as industry,Academia,Academia.

When was CamemBERT released?

CamemBERT was published in November 2019. 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 CamemBERT used for?

CamemBERT works in Language, and is recorded as handling language modeling/generation, Part-of-speech tagging, Named entity recognition (NER). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download CamemBERT?

The weights for CamemBERT 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 CamemBERT?

Around 8.3 × 10²⁰ FLOP, on NVIDIA V100. 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 CamemBERT if it does not fit in my GPU?

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

Would two GPUs run CamemBERT faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run CamemBERT alone, the case for pairing is weak.

Why does the quantisation differ between cards for CamemBERT?

Each card is shown running the least-compressed copy it can hold, and CamemBERT appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these CamemBERT speed estimates?

These are estimates with real error bars. The fastest result here, 6,068–16,183 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 CamemBERT?

The smallest card in our catalogue that holds CamemBERT is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.1 GB, and produces roughly 110 tokens per second. 818 cards in total can run it.

How fast is CamemBERT on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 10,114 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 CamemBERT clear that.

How much VRAM does CamemBERT 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 CamemBERT 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 1,884 tokens per second — a comfortable fit.

Can I run CamemBERT 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 1,154 tokens per second — a comfortable fit.

Can I run CamemBERT 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 1,429 tokens per second — a comfortable fit.

Can I run CamemBERT 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 1,694 tokens per second — a comfortable fit.

Is CamemBERT open source?

Its weights are published, so CamemBERT 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