MSA Transformer TPS calculator

Open weights Facebook AI Research,University of California (UC) Berkeley,New York University (NYU) 100M parameters February 2021

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 · 369 tok/s

Fastest card

B200

33,882 tok/s · 180 GB

Which GPUs can run MSA Transformer?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

818 cards match

Calculating
Needs Quantisation Fit
33,882 tok/s

20,329–54,212 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 0.8 GB Q8_0 Comfortable
33,882 tok/s

20,329–54,212 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 0.8 GB Q8_0 Comfortable
27,056 tok/s

16,234–43,289 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 0.8 GB Q8_0 Comfortable
27,056 tok/s

16,234–43,289 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 0.8 GB Q8_0 Comfortable
21,638 tok/s

12,983–34,621 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 0.8 GB Q8_0 Comfortable
20,711 tok/s

12,426–33,137 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 0.8 GB Q8_0 Comfortable
20,711 tok/s

12,426–33,137 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 0.8 GB Q8_0 Comfortable
19,821 tok/s

11,893–31,714 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 0.8 GB Q8_0 Comfortable
17,591 tok/s

10,555–28,146 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 0.8 GB Q8_0 Comfortable
17,591 tok/s

10,555–28,146 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 0.8 GB Q8_0 Comfortable
17,591 tok/s

10,555–28,146 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 0.8 GB Q8_0 Comfortable
16,687 tok/s

10,012–26,699 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 0.8 GB Q8_0 Comfortable
14,231 tok/s

8,538–22,769 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 0.8 GB Q8_0 Comfortable
14,231 tok/s

8,538–22,769 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 0.8 GB Q8_0 Comfortable
14,231 tok/s

8,538–22,769 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 0.8 GB Q8_0 Comfortable
14,231 tok/s

8,538–22,769 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 0.8 GB Q8_0 Comfortable
14,231 tok/s

8,538–22,769 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 0.8 GB Q8_0 Comfortable
10,836 tok/s

6,501–17,337 · low confidence

Radeon Instinct MI250 AMD 128 GB 3,280 GB/s Nov 2021 0.8 GB Q8_0 Comfortable
10,836 tok/s

6,501–17,337 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 0.8 GB Q8_0 Comfortable
9,030 tok/s

5,418–14,447 · low confidence

Data Center GPU Max 1550 Intel 128 GB 3,280 GB/s Jan 2023 0.8 GB Q8_0 Comfortable
8,837 tok/s

5,302–14,139 · low confidence

Data Center GPU Max Subsystem Intel 128 GB 3,210 GB/s Jan 2023 0.8 GB Q8_0 Comfortable
8,640 tok/s

5,184–13,824 · low confidence

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 0.8 GB Q8_0 Comfortable
8,640 tok/s

5,184–13,824 · low confidence

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 0.8 GB Q8_0 Comfortable
8,640 tok/s

5,184–13,824 · low confidence

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 0.8 GB Q8_0 Comfortable
8,640 tok/s

5,184–13,824 · 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
Facebook AI Research,University of California (UC) Berkeley,New York University (NYU)
Organisation type
Industry,Academia,Academia
Country
United States of America, France
Published
13 February 2021
Authors
Roshan Rao, Jason Liu, Robert Verkuil, Joshua Meier, John F. Canny, Pieter Abbeel, Tom Sercu, Alexander Rives

What it does

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

Domain
Biology
Task
Proteins, Protein or nucleotide language model (pLM/nLM), Protein contact and distance prediction, Protein folding prediction

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
100M

"We train an MSA Transformer model with 100M parameters..."

Training data
1,395,000,000,000 tokens

"We train an MSA Transformer model with 100M parameters on a large dataset (4.3 TB) of 26 million MSAs, with an average of 1192 sequences per MSA." Average sequence is ~300 amino acids/tokens long. 26 million * 1192 * 300 = 9.3T 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
5.5 × 10²¹ FLOP

Based on: https://docs.google.com/spreadsheets/d/1enan21dFx03TkwufHgOwTVNBtuYlqNY9uurjIK6YS-8/edit#gid=0 Number of steps 4.5e5, batch size (tokens) 6.1e7, parameters 1e8 Calculation = 4e8 FLOP/bp * 4.5e5 bp + 2e8 FLOP/fp * 2.75e13 fp Batch size: 512 Seq length: 100 * 1192 tokens All models are trained on 32 V100 GPUs for 100k updates. The four models with best contact precision are then further trained to 150k updates. Finally, the best model at 150k updates is trained to 450k updates. 450k …

How it was established
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 Tesla V100 DGXS 32 GB
Chips used
32
Power draw
16.2 kW
Compute cost
$13,257

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

MIT: https://github.com/facebookresearch/esm looks like no training code

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

"The performance of the model surpasses current state-of-the-art unsupervised structure learning methods by a wide margin, with far greater parameter efficiency than prior state-of-the-art protein language models"

Record confidence
Likely
Citations
644

Sources

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

Reference
MSA Transformer
Last updated
1 January 2026

The extremes

The ten fastest GPUs that run MSA Transformer

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.

  1. 01 B300 288 GB · 8,000 GB/s · Q8_0 33,882 tok/s
  2. 02 B200 180 GB · 8,000 GB/s · Q8_0 33,882 tok/s
  3. 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 27,056 tok/s
  4. 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 27,056 tok/s
  5. 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 21,638 tok/s
  6. 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 20,711 tok/s
  7. 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 20,711 tok/s
  8. 08 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 19,821 tok/s
  9. 09 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q8_0 17,591 tok/s
  10. 10 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q8_0 17,591 tok/s

The smallest GPUs that still run MSA Transformer

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

  1. 01 GeForce RTX 4010 4 GB · needs 0.8 GB · Q8_0 · comfortable 407 tok/s
  2. 02 RTX A400 4 GB · needs 0.8 GB · Q8_0 · comfortable 407 tok/s
  3. 03 RTX 500 Mobile Ada Generation 4 GB · needs 0.8 GB · Q8_0 · comfortable 542 tok/s
  4. 04 GeForce RTX 3050 A Mobile 4 GB · needs 0.8 GB · Q8_0 · comfortable 813 tok/s
  5. 05 Jetson Orin Nano 4 GB 4 GB · needs 0.8 GB · Q8_0 · comfortable 144 tok/s
  6. 06 Radeon RX 6450M 4 GB · needs 0.8 GB · Q8_0 · comfortable 423 tok/s
  7. 07 Radeon RX 6550M 4 GB · needs 0.8 GB · Q8_0 · comfortable 476 tok/s
  8. 08 Radeon RX 6550S 4 GB · needs 0.8 GB · Q8_0 · comfortable 423 tok/s
  9. 09 Arc A310 4 GB · needs 0.8 GB · Q8_0 · comfortable 341 tok/s
  10. 10 Arc Pro A30M 4 GB · needs 0.8 GB · Q8_0 · comfortable 352 tok/s

What the numbers mean

The hardware side

Minimum card

Tesla C1080

Memory needed

0.8 GB

Fastest

33,882 tok/s

MSA Transformer is small enough at 100M 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 369 tokens per second.

A B200 is the fastest we calculate for it: about 33,882 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

MSA Transformer was published by Facebook AI Research,University of California (UC) Berkeley,New York University (NYU), in United States of America, in February 2021. industry,Academia,Academia is the category the publisher falls under.

It works in Biology, and is recorded as doing proteins, Protein or nucleotide language model (pLM/nLM), Protein contact and distance prediction, Protein folding prediction.

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

Reading the throughput figures

Half the cards that hold it manage more than 951.4 tokens per second, and 818 exceed reading speed outright.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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.

How it was trained

The training run consumed about 5.5 × 10²¹ FLOP, on NVIDIA Tesla V100 DGXS 32 GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Around 1,395,000,000,000 tokens went into training it.

The reason it appears in this catalogue at all is sOTA improvement.

Step by step

How to choose a GPU for MSA Transformer

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

  1. 01

    Start from the memory column

    Look at what MSA Transformer actually needs — around 0.8 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.

  2. 02

    Set the context length you will work at

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

  3. 03

    Choose how far you will compress it

    Compression is what makes MSA Transformer 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.

  4. 04

    Compare tokens per second, not specifications

    Sort by speed to see how cards rank for MSA Transformer. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 33,882 tok/s.

  5. 05

    Check the fit verdict before buying

    A tight fit runs MSA Transformer but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.

  6. 06

    See what else that card runs

    Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for MSA Transformer alone — a card is usually bought for more than one model.

Answers

MSA Transformer — common questions

01

Can I run MSA Transformer 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 5,675 tokens per second — a comfortable fit.

02

Is MSA Transformer open source?

Its weights are published, so MSA Transformer 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.

03

How many parameters does MSA Transformer have?

MSA Transformer has 100M parameters. "We train an MSA Transformer model with 100M 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.

04

Who created MSA Transformer?

MSA Transformer was published by Facebook AI Research,University of California (UC) Berkeley,New York University (NYU), based in United States of America, categorised as industry,Academia,Academia.

05

When was MSA Transformer released?

MSA Transformer was published in February 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is MSA Transformer used for?

MSA Transformer works in Biology, and is recorded as handling proteins, Protein or nucleotide language model (pLM/nLM), Protein contact and distance prediction, Protein folding prediction. 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.

07

Where can I download MSA Transformer?

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

08

How much compute was used to train MSA Transformer?

Around 5.5 × 10²¹ FLOP, on NVIDIA Tesla V100 DGXS 32 GB. 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.

09

Can I run MSA Transformer if it does not fit in my GPU?

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

10

Would two GPUs run MSA Transformer faster?

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

11

Why does the quantisation differ between cards for MSA Transformer?

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

12

How accurate are these MSA Transformer speed estimates?

These are estimates with real error bars. The fastest result here, 20,329–54,212 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

13

What GPU do I need to run MSA Transformer?

The smallest card in our catalogue that holds MSA Transformer is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.8 GB, and produces roughly 369 tokens per second. 818 cards in total can run it.

14

How fast is MSA Transformer on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 33,882 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 MSA Transformer clear that.

15

How much VRAM does MSA Transformer 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.

16

Can I run MSA Transformer 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 6,311 tokens per second — a comfortable fit.

17

Can I run MSA Transformer 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 3,864 tokens per second — a comfortable fit.

18

Can I run MSA Transformer 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 4,786 tokens per second — a comfortable fit.

Source

Original publication

Record last updated 1 January 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