AlphaLink TPS calculator

Open weights Technische Universitat Berlin,Research Cluster of Excellence,University of Edinburgh 93M parameters April 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 · 396 tok/s

Fastest card

B200

36,433 tok/s · 180 GB

Which GPUs can run AlphaLink?

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: Technische Universitat Berlin,Research Cluster of Excellence,University of Edinburgh
Organisation type: Academia,Research collective,Academia
Country: Germany, United Kingdom of Great Britain and Northern Ireland
Published: 20 April 2023
Authors: Kolja Stahl, Andrea Graziadei, Therese Dau, Oliver Brock, Juri Rappsilber

What it does

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

Domain: Biology
Task: Protein folding prediction
Base model: AlphaFold 2

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
Epochs: 5

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.

How it was established: Hardware
Fine-tuning compute: 2 × 10²⁰ FLOP

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Chips used: 5
Wall-clock time: 120 hours

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: Speculative

Sources

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

Reference: Protein structure prediction with in-cell photo-crosslinking mass spectrometry and deep learning
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run AlphaLink

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 AlphaLink

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

AlphaLink 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.

The quickest result comes from a B200 at around 36,433 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

AlphaLink was published by Technische Universitat Berlin,Research Cluster of Excellence,University of Edinburgh, in Germany, in April 2023. The organisation is categorised as academia,Research collective,Academia.

It works in Biology, and is recorded as doing protein folding prediction.

It is derived from AlphaFold 2 rather than trained from scratch, which is the usual way a specialised model is produced.

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.

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

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.

Step by step

How to choose a GPU for AlphaLink

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

Look at what AlphaLink actually needs — around 0.8 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
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 AlphaLink can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

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 AlphaLink by squeezing it further than you would want.
04

Rank by throughput rather than spec sheet

The speed ordering for AlphaLink is effectively an ordering 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 AlphaLink from those with room to spare. Buy for the second if the context might grow.
06

See what else that card runs

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond AlphaLink.

Answers

AlphaLink — common questions

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

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down. Our figures for AlphaLink assume it is fully resident.

Would two GPUs run AlphaLink faster?

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

Why does the quantisation differ between cards for AlphaLink?

Because capacity varies, so does how hard AlphaLink has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these AlphaLink speed estimates?

These are estimates with real error bars. The fastest result here, 21,860–58,292 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 AlphaLink?

The smallest card in our catalogue that holds AlphaLink 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 AlphaLink 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 AlphaLink clear that.

How much VRAM does AlphaLink 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 AlphaLink 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 AlphaLink 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 AlphaLink 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 AlphaLink 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 AlphaLink open source?

Its weights are published, so AlphaLink 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 AlphaLink have?

AlphaLink has 93M parameters. "To avoid training OpenFold from scratch, we start with the AlphaFold2 2.0 (https://github.com/deepmind/alphafold/releases/tag/v2.0.0) weights provided by Deepmind". 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 AlphaLink?

AlphaLink was published by Technische Universitat Berlin,Research Cluster of Excellence,University of Edinburgh, based in Germany, categorised as academia,Research collective,Academia.

When was AlphaLink released?

AlphaLink was published in April 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 AlphaLink used for?

AlphaLink works in Biology, and is recorded as handling protein folding prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download AlphaLink?

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

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