Ankh_large TPS calculator

Open weights Technical University of Munich,Columbia University 1.9B parameters January 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 · 19.4 tok/s

Fastest card

B200

1,783 tok/s · 180 GB

Which GPUs can run Ankh_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
1,783 tok/s 1,070–2,853 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.7 GB	Q8_0	Comfortable
1,783 tok/s 1,070–2,853 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.7 GB	Q8_0	Comfortable
1,424 tok/s 854–2,278 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.7 GB	Q8_0	Comfortable
1,424 tok/s 854–2,278 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.7 GB	Q8_0	Comfortable
1,139 tok/s 683–1,822 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.7 GB	Q8_0	Comfortable
1,090 tok/s 654–1,744 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.7 GB	Q8_0	Comfortable
1,090 tok/s 654–1,744 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.7 GB	Q8_0	Comfortable
1,043 tok/s 626–1,669 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.7 GB	Q8_0	Comfortable
926 tok/s 556–1,481 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.7 GB	Q8_0	Comfortable
926 tok/s 556–1,481 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.7 GB	Q8_0	Comfortable
926 tok/s 556–1,481 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.7 GB	Q8_0	Comfortable
878 tok/s 527–1,405 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.7 GB	Q8_0	Comfortable
749 tok/s 449–1,198 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.7 GB	Q8_0	Comfortable
749 tok/s 449–1,198 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.7 GB	Q8_0	Comfortable
749 tok/s 449–1,198 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.7 GB	Q8_0	Comfortable
749 tok/s 449–1,198 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.7 GB	Q8_0	Comfortable
749 tok/s 449–1,198 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.7 GB	Q8_0	Comfortable
570 tok/s 342–912 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.7 GB	Q8_0	Comfortable
570 tok/s 342–912 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.7 GB	Q8_0	Comfortable
475 tok/s 285–760 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.7 GB	Q8_0	Comfortable
465 tok/s 279–744 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.7 GB	Q8_0	Comfortable
455 tok/s 273–728 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.7 GB	Q8_0	Comfortable
455 tok/s 273–728 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.7 GB	Q8_0	Comfortable
455 tok/s 273–728 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.7 GB	Q8_0	Comfortable
455 tok/s 273–728 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.7 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,Columbia University
Organisation type: Academia,Academia
Country: Germany, United States of America
Published: 16 January 2023
Authors: Ahmed Elnaggar, Hazem Essam, Wafaa Salah-Eldin, Walid Moustafa, Mohamed Elkerdawy, Charlotte Rochereau, Burkhard Rost

What it does

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

Domain: Biology
Task: Protein generation, Proteins, Protein or nucleotide language model (pLM/nLM), Protein contact and distance prediction, Protein classification, Protein localization prediction, Protein fold classification

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: 1.9B
Training data: 14,000,000,000 tokens
Epochs: 68
Batch size: 524,288

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: 6.5 × 10²¹ FLOP
How it was established: Operation counting,Third-party estimation

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: Google TPU v4
Chips used: 64
Power draw: 43.5 kW
Compute cost: $4,802

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 (non-commercial)
Training code: Unreleased
Hugging Face: ElnaggarLab

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
Record confidence: Confident
Citations: 159

Sources

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

Reference: Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Ankh_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 Ankh_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

What you need to run it

Minimum card

Tesla C1080

Memory needed

2.7 GB

Fastest

1,783 tok/s

Ankh_large is small enough at 1.9B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 19.4 tokens per second.

Top of the range is the B200, at roughly 1,783 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

Ankh_large was published by Technical University of Munich,Columbia University, in Germany, in January 2023. The organisation is categorised as academia,Academia.

It works in Biology, and is recorded as doing protein generation, Proteins, Protein or nucleotide language model (pLM/nLM), Protein contact and distance prediction, Protein classification, Protein localization prediction, Protein fold classification.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the ElnaggarLab organisation on Hugging Face.

How fast it runs, and why

Half the cards that hold it manage more than 50.1 tokens per second, and 789 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.

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

The training run consumed about 6.5 × 10²¹ FLOP, on Google TPU v4. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 14,000,000,000 tokens of text.

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

Step by step

How to choose a GPU for Ankh_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

The table lists every card that can hold Ankh_large — around 2.7 GB at Q8_0. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Ankh_large stops fitting a card that seemed fine.
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of Ankh_large — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Sort by speed

The speed ordering for Ankh_large is effectively an ordering by memory bandwidth, which is why the B200 tops it at 1,783 tok/s.
05

Check the fit verdict before buying

A tight fit runs Ankh_large but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

Check the card from the other side

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

Answers

Ankh_large — common questions

Can I run Ankh_large on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.7 GB and generating roughly 299 tokens per second — a comfortable fit.

Is Ankh_large open source?

Its weights are published, so Ankh_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 Ankh_large have?

Ankh_large has 1.9B parameters. Figure 1 indicates 1.15B parameters, but both the huggingface model and a replication (https://huggingface.co/ElnaggarLab/ankh-large and https://www.biorxiv.org/content/10.1101/2023.07.05.547496v1.full.pdf) indicate 1.9B parameters. Notebook for counting params: https://colab.research.google.com/drive/1EGI5_vDl4pOBUukJexMHQR16BFKJe4a5?usp=sharing. 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 Ankh_large?

Ankh_large was published by Technical University of Munich,Columbia University, based in Germany, categorised as academia,Academia.

When was Ankh_large released?

Ankh_large was published in January 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 Ankh_large used for?

Ankh_large works in Biology, and is recorded as handling protein generation, Proteins, Protein or nucleotide language model (pLM/nLM), Protein contact and distance prediction, Protein classification, Protein localization prediction, Protein fold classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Ankh_large?

Its weights are published under the ElnaggarLab organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train Ankh_large?

Around 6.5 × 10²¹ FLOP, on Google TPU v4. 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 Ankh_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 Ankh_large is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run Ankh_large faster?

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

Why does the quantisation differ between cards for Ankh_large?

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

How accurate are these Ankh_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 1,070–2,853 tok/s on the B200 rather than a single number.

What GPU do I need to run Ankh_large?

The smallest card in our catalogue that holds Ankh_large is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.7 GB, and produces roughly 19.4 tokens per second. 818 cards in total can run it.

How fast is Ankh_large on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,783 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 789 of the cards that can run Ankh_large clear that.

How much VRAM does Ankh_large need?

About 2.7 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 Ankh_large on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.7 GB and generating roughly 332 tokens per second — a comfortable fit.

Can I run Ankh_large on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.7 GB and generating roughly 203 tokens per second — a comfortable fit.

Can I run Ankh_large on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.7 GB and generating roughly 252 tokens per second — a comfortable fit.

Source

Original publication

Record last updated 25 May 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