Multilingual-E5-large TPS calculator

Open weights Microsoft 560M parameters June 2023

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 · 65.8 tok/s

Fastest card

B200

6,050 tok/s · 180 GB

Which GPUs can run Multilingual-E5-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
6,050 tok/s 3,630–9,681 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.3 GB	Q8_0	Comfortable
6,050 tok/s 3,630–9,681 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.3 GB	Q8_0	Comfortable
4,831 tok/s 2,899–7,730 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.3 GB	Q8_0	Comfortable
4,831 tok/s 2,899–7,730 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.3 GB	Q8_0	Comfortable
3,864 tok/s 2,318–6,182 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.3 GB	Q8_0	Comfortable
3,698 tok/s 2,219–5,917 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.3 GB	Q8_0	Comfortable
3,698 tok/s 2,219–5,917 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.3 GB	Q8_0	Comfortable
3,540 tok/s 2,124–5,663 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.3 GB	Q8_0	Comfortable
3,141 tok/s 1,885–5,026 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.3 GB	Q8_0	Comfortable
3,141 tok/s 1,885–5,026 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.3 GB	Q8_0	Comfortable
3,141 tok/s 1,885–5,026 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.3 GB	Q8_0	Comfortable
2,980 tok/s 1,788–4,768 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.3 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
2,541 tok/s 1,525–4,066 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.3 GB	Q8_0	Comfortable
1,935 tok/s 1,161–3,096 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.3 GB	Q8_0	Comfortable
1,935 tok/s 1,161–3,096 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.3 GB	Q8_0	Comfortable
1,612 tok/s 967–2,580 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.3 GB	Q8_0	Comfortable
1,578 tok/s 947–2,525 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.3 GB	Q8_0	Comfortable
1,543 tok/s 926–2,469 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.3 GB	Q8_0	Comfortable
1,543 tok/s 926–2,469 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.3 GB	Q8_0	Comfortable
1,543 tok/s 926–2,469 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.3 GB	Q8_0	Comfortable
1,543 tok/s 926–2,469 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.3 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: Microsoft
Organisation type: Industry
Country: United States of America
Published: 30 June 2023
Authors: Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei

What it does

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

Domain: Language
Task: Semantic embedding

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: 560M
Training data: 1,000,160,000 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: 3.4 × 10¹⁸ FLOP
How it was established: Operation counting

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.

Record confidence: Likely

Sources

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

Reference: Multilingual E5 Text Embeddings: A Technical Report
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Multilingual-E5-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 Multilingual-E5-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

The hardware side

Minimum card

Tesla C1080

Memory needed

1.3 GB

Fastest

6,050 tok/s

Multilingual-E5-large is small enough at 560M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

At the low end, a Tesla C1080 handles it — 4 GB, at Q8_0, for about 65.8 tokens per second.

The quickest result comes from a B200 at around 6,050 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

What this model is

Multilingual-E5-large was published by Microsoft, in United States of America, in June 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing semantic embedding.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

What decides the speed

The median result is around 169.9 tokens per second; 809 cards produce text faster than most people read it.

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

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.

Training and provenance

Training it took roughly 3.4 × 10¹⁸ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Around 1,000,160,000 tokens went into training it.

Step by step

How to choose a GPU for Multilingual-E5-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

Every card here has been checked against Multilingual-E5-large — around 1.3 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

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Multilingual-E5-large.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage Multilingual-E5-large by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for Multilingual-E5-large follows memory bandwidth, not core counts, which is why the B200 tops it at 6,050 tok/s.
05

Look at the headroom, not just the fit

Tight means Multilingual-E5-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

Open the card you have settled on

Following a card through to its own page shows every other model it can hold, which is the question that follows once Multilingual-E5-large is settled.

Answers

Multilingual-E5-large — common questions

Why does the quantisation differ between cards for Multilingual-E5-large?

Each card is shown running the least-compressed copy it can hold, and Multilingual-E5-large appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Multilingual-E5-large 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 3,630–9,681 tok/s on the B200 rather than a single number.

What GPU do I need to run Multilingual-E5-large?

The smallest card in our catalogue that holds Multilingual-E5-large is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.3 GB, and produces roughly 65.8 tokens per second. 818 cards in total can run it.

How fast is Multilingual-E5-large on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 6,050 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 809 of the cards that can run Multilingual-E5-large clear that.

How much VRAM does Multilingual-E5-large need?

About 1.3 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 Multilingual-E5-large on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.3 GB and generating roughly 1,127 tokens per second — a comfortable fit.

Can I run Multilingual-E5-large on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.3 GB and generating roughly 690 tokens per second — a comfortable fit.

Can I run Multilingual-E5-large on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.3 GB and generating roughly 855 tokens per second — a comfortable fit.

Can I run Multilingual-E5-large on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.3 GB and generating roughly 1,013 tokens per second — a comfortable fit.

Is Multilingual-E5-large open source?

Its weights are published, so Multilingual-E5-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.

How many parameters does Multilingual-E5-large have?

Multilingual-E5-large has 560M parameters. 560M from https://huggingface.co/intfloat/multilingual-e5-large. 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 Multilingual-E5-large?

Multilingual-E5-large was published by Microsoft, based in United States of America, categorised as industry.

When was Multilingual-E5-large released?

Multilingual-E5-large was published in June 2023. 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 Multilingual-E5-large used for?

Multilingual-E5-large works in Language, and is recorded as handling semantic embedding. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Multilingual-E5-large?

The weights for Multilingual-E5-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 Multilingual-E5-large?

Around 3.4 × 10¹⁸ FLOP. 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 Multilingual-E5-large if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded Multilingual-E5-large is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run Multilingual-E5-large faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run Multilingual-E5-large alone, the case for pairing is weak.

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