BGE-M3 Embedding TPS calculator

Open weights Beijing Academy of Artificial Intelligence / BAAI 335M parameters January 2024

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 BGE-M3 Embedding?

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: Beijing Academy of Artificial Intelligence / BAAI
Organisation type: Academia
Country: China
Published: 30 January 2024
Authors: Jianlv Chen, Shitao Xiao, Peitian Zhan, Kun Luo, Defu Lian, Zheng Liu

What it does

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

Domain: Language
Task: Language modeling/generation, Translation
Base model: XLM-RoBERTa

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: 1,201,100,000 tokens

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 A100,NVIDIA A800 PCIe 40 GB

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.

Record confidence: Likely

Sources

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

Reference: BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run BGE-M3 Embedding

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 BGE-M3 Embedding

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

10,114 tok/s

BGE-M3 Embedding 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 smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 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.

Background

BGE-M3 Embedding was published by Beijing Academy of Artificial Intelligence / BAAI, in China, in January 2024. academia is the category the publisher falls under.

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

It is derived from XLM-RoBERTa rather than trained from scratch, which is the usual way a specialised model is produced.

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.

Reading the throughput figures

Half the cards that hold it manage more than 284.0 tokens per second, and 818 exceed reading speed outright.

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.

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

The training set ran to roughly 1,201,100,000 tokens.

Step by step

How to choose a GPU for BGE-M3 Embedding

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

Every card here has been checked against BGE-M3 Embedding — around 1.1 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason BGE-M3 Embedding stops fitting a card that seemed fine.
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 BGE-M3 Embedding by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

The speed ordering for BGE-M3 Embedding is effectively an ordering by memory bandwidth, which is why the B200 tops it at 10,114 tok/s.
05

Read the fit column last

The fit column separates cards that just manage BGE-M3 Embedding from those with room to spare. Buy for the second if the context might grow.
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 BGE-M3 Embedding is settled.

Answers

BGE-M3 Embedding — common questions

What GPU do I need to run BGE-M3 Embedding?

The smallest card in our catalogue that holds BGE-M3 Embedding 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 BGE-M3 Embedding 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 BGE-M3 Embedding clear that.

How much VRAM does BGE-M3 Embedding 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 BGE-M3 Embedding 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 BGE-M3 Embedding 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 BGE-M3 Embedding 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 BGE-M3 Embedding 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 BGE-M3 Embedding open source?

Its weights are published, so BGE-M3 Embedding 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 BGE-M3 Embedding have?

BGE-M3 Embedding has 335M parameters. 335M params (from Hugging Face model card). 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 BGE-M3 Embedding?

BGE-M3 Embedding was published by Beijing Academy of Artificial Intelligence / BAAI, based in China, categorised as academia.

When was BGE-M3 Embedding released?

BGE-M3 Embedding was published in January 2024. 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 BGE-M3 Embedding used for?

BGE-M3 Embedding works in Language, and is recorded as handling language modeling/generation, Translation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download BGE-M3 Embedding?

The weights for BGE-M3 Embedding are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run BGE-M3 Embedding 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 BGE-M3 Embedding is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run BGE-M3 Embedding faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold BGE-M3 Embedding on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for BGE-M3 Embedding?

A larger card holds a more accurate copy. Across the cards that run BGE-M3 Embedding, 1 compression levels are used; the floor control above pins it to one.

How accurate are these BGE-M3 Embedding 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 6,068–16,183 tok/s on the B200 rather than a single number.

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