SeqVec TPS calculator

Open weights Technical University of Munich 93M parameters December 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 · 396 tok/s

Fastest card

B200

36,433 tok/s · 180 GB

Which GPUs can run SeqVec?

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
36,433 tok/s 21,860–58,292 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.8 GB	Q8_0	Comfortable
36,433 tok/s 21,860–58,292 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.8 GB	Q8_0	Comfortable
29,092 tok/s 17,455–46,548 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.8 GB	Q8_0	Comfortable
29,092 tok/s 17,455–46,548 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.8 GB	Q8_0	Comfortable
23,267 tok/s 13,960–37,227 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
22,269 tok/s 13,362–35,631 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.8 GB	Q8_0	Comfortable
22,269 tok/s 13,362–35,631 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.8 GB	Q8_0	Comfortable
21,313 tok/s 12,788–34,101 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.8 GB	Q8_0	Comfortable
18,915 tok/s 11,349–30,265 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
18,915 tok/s 11,349–30,265 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
18,915 tok/s 11,349–30,265 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.8 GB	Q8_0	Comfortable
17,943 tok/s 10,766–28,709 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
15,302 tok/s 9,181–24,483 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
15,302 tok/s 9,181–24,483 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.8 GB	Q8_0	Comfortable
15,302 tok/s 9,181–24,483 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
15,302 tok/s 9,181–24,483 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
15,302 tok/s 9,181–24,483 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.8 GB	Q8_0	Comfortable
11,651 tok/s 6,991–18,642 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.8 GB	Q8_0	Comfortable
11,651 tok/s 6,991–18,642 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.8 GB	Q8_0	Comfortable
9,709 tok/s 5,826–15,535 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
9,502 tok/s 5,701–15,203 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.8 GB	Q8_0	Comfortable
9,290 tok/s 5,574–14,865 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.8 GB	Q8_0	Comfortable
9,290 tok/s 5,574–14,865 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.8 GB	Q8_0	Comfortable
9,290 tok/s 5,574–14,865 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.8 GB	Q8_0	Comfortable
9,290 tok/s 5,574–14,865 · 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: Technical University of Munich
Organisation type: Academia
Country: Germany
Published: 17 December 2019
Authors: Michael Heinzinger, Ahmed Elnaggar, Yu Wang, Christian Dallago, Dmitrii Nechaev, Florian Matthes & Burkhard Rost

What it does

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

Domain: Biology
Task: Proteins

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: 93M
Training data: 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: 4.1 × 10¹⁹ FLOP
How it was established: Hardware

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 Titan V
Chips used: 5
Chip-hours: 2,540
Wall-clock time: 508 hours (21.2 days)
Power draw: 2.6 kW

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: Confident

Sources

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

Reference: Modeling aspects of the language of life through transfer-learning protein sequences
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run SeqVec

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 SeqVec

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

Hardware requirements in practice

Minimum card

Tesla C1080

Memory needed

0.8 GB

Fastest

36,433 tok/s

SeqVec is small enough at 93M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q8_0 compression, roughly 396 tokens per second.

Top of the range is the B200, at roughly 36,433 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

SeqVec was published by Technical University of Munich, in Germany, in December 2019. The organisation is categorised as academia.

It works in Biology, and is recorded as doing proteins.

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

Reading the throughput figures

The median result is around 1,023.0 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.

How it was trained

Training it took roughly 4.1 × 10¹⁹ FLOP of computation, on NVIDIA Titan V — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for SeqVec

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 SeqVec — around 0.8 GB at Q8_0. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for SeqVec.
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 SeqVec by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

Sort by speed to see how cards rank for SeqVec. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 36,433 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage SeqVec from those with room to spare. Buy for the second if the context might grow.
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 SeqVec alone — a card is usually bought for more than one model.

Answers

SeqVec — common questions

Would two GPUs run SeqVec faster?

Two cards buy memory rather than speed. That matters for SeqVec only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for SeqVec?

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

How accurate are these SeqVec speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 21,860–58,292 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run SeqVec?

The smallest card in our catalogue that holds SeqVec is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.8 GB, and produces roughly 396 tokens per second. 818 cards in total can run it.

How fast is SeqVec on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 36,433 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 SeqVec clear that.

How much VRAM does SeqVec 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.

Can I run SeqVec 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 6,786 tokens per second — a comfortable fit.

Can I run SeqVec 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 4,155 tokens per second — a comfortable fit.

Can I run SeqVec 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 5,146 tokens per second — a comfortable fit.

Can I run SeqVec 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 6,102 tokens per second — a comfortable fit.

Is SeqVec open source?

Its weights are published, so SeqVec 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 SeqVec have?

SeqVec has 93M parameters. "The model had about 93 M (mega/million) free 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.

Who created SeqVec?

SeqVec was published by Technical University of Munich, based in Germany, categorised as academia.

When was SeqVec released?

SeqVec was published in December 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 SeqVec used for?

SeqVec works in Biology, and is recorded as handling proteins. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download SeqVec?

The weights for SeqVec 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 SeqVec?

Around 4.1 × 10¹⁹ FLOP, on NVIDIA Titan V. 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 SeqVec if it does not fit in my GPU?

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

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