DistilProtBert TPS calculator

Open weights Bar-Ilan University 230M parameters September 2022

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 · 160 tok/s

Fastest card

B200

14,731 tok/s · 180 GB

Which GPUs can run DistilProtBert?

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
14,731 tok/s 8,839–23,570 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	0.9 GB	Q8_0	Comfortable
14,731 tok/s 8,839–23,570 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	0.9 GB	Q8_0	Comfortable
11,763 tok/s 7,058–18,822 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
11,763 tok/s 7,058–18,822 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	0.9 GB	Q8_0	Comfortable
9,408 tok/s 5,645–15,053 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
9,005 tok/s 5,403–14,407 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
9,005 tok/s 5,403–14,407 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	0.9 GB	Q8_0	Comfortable
8,618 tok/s 5,171–13,789 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	0.9 GB	Q8_0	Comfortable
7,648 tok/s 4,589–12,237 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
7,648 tok/s 4,589–12,237 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
7,648 tok/s 4,589–12,237 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	0.9 GB	Q8_0	Comfortable
7,255 tok/s 4,353–11,608 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
6,187 tok/s 3,712–9,900 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
6,187 tok/s 3,712–9,900 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	0.9 GB	Q8_0	Comfortable
6,187 tok/s 3,712–9,900 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
6,187 tok/s 3,712–9,900 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
6,187 tok/s 3,712–9,900 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	0.9 GB	Q8_0	Comfortable
4,711 tok/s 2,827–7,538 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
4,711 tok/s 2,827–7,538 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	0.9 GB	Q8_0	Comfortable
3,926 tok/s 2,356–6,281 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
3,842 tok/s 2,305–6,147 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	0.9 GB	Q8_0	Comfortable
3,757 tok/s 2,254–6,010 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	0.9 GB	Q8_0	Comfortable
3,757 tok/s 2,254–6,010 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	0.9 GB	Q8_0	Comfortable
3,757 tok/s 2,254–6,010 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	0.9 GB	Q8_0	Comfortable
3,757 tok/s 2,254–6,010 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	0.9 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: Bar-Ilan University
Organisation type: Academia
Country: Israel
Published: 18 September 2022
Authors: Yaron Geffen, Yanay Ofran, Ron Unger

What it does

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

Domain: Biology
Task: Proteins, 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: 230M
Training data: 11,008,000,000 tokens
Epochs: 3

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: 1.9 × 10²⁰ 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 Tesla V100 DGXS 32 GB
Wall-clock time: 288 hours (12 days)

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
Hugging Face: yarongef

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence: Confident
Citations: 39

Sources

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

Reference: DistilProtBert: a distilled protein language model used to distinguish between real proteins and their randomly shuffled counterparts
Last updated: 1 January 2026

The extremes

The ten fastest GPUs that run DistilProtBert

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 DistilProtBert

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

The hardware side

Minimum card

Tesla C1080

Memory needed

0.9 GB

Fastest

14,731 tok/s

DistilProtBert is small enough at 230M 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 160 tokens per second.

The quickest result comes from a B200 at around 14,731 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Where it came from

DistilProtBert was published by Bar-Ilan University, in Israel, in September 2022. academia is the category the publisher falls under.

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

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the yarongef organisation on Hugging Face.

Understanding the speeds

Half the cards that hold it manage more than 413.7 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

Producing it required around 1.9 × 10²⁰ FLOP of arithmetic, on NVIDIA Tesla V100 DGXS 32 GB, which is a statement about the training budget rather than about inference.

The training set ran to roughly 11,008,000,000 tokens.

Step by step

How to choose a GPU for DistilProtBert

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

Look at what DistilProtBert actually needs — around 0.9 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

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

Set a quality floor

Compression is what makes DistilProtBert 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.
04

Sort by speed

The speed ordering for DistilProtBert is effectively an ordering by memory bandwidth, which is why the B200 tops it at 14,731 tok/s.
05

Read the fit column last

Tight means DistilProtBert loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
06

Open the card you have settled on

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

Answers

DistilProtBert — common questions

Can I run DistilProtBert on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 0.9 GB and generating roughly 1,680 tokens per second — a comfortable fit.

Can I run DistilProtBert on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,081 tokens per second — a comfortable fit.

Can I run DistilProtBert on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,468 tokens per second — a comfortable fit.

Is DistilProtBert open source?

Its weights are published, so DistilProtBert 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 DistilProtBert have?

DistilProtBert has 230M parameters. "we were able to reduce the number of DistilProtBert parameters by almost half, to 230 M". 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 DistilProtBert?

DistilProtBert was published by Bar-Ilan University, based in Israel, categorised as academia.

When was DistilProtBert released?

DistilProtBert was published in September 2022. 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 DistilProtBert used for?

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

Where can I download DistilProtBert?

Its weights are published under the yarongef 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 DistilProtBert?

Around 1.9 × 10²⁰ 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.

Can I run DistilProtBert 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 DistilProtBert assume it is fully resident.

Would two GPUs run DistilProtBert faster?

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

Why does the quantisation differ between cards for DistilProtBert?

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

How accurate are these DistilProtBert 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 8,839–23,570 tok/s on the B200 rather than a single number.

What GPU do I need to run DistilProtBert?

The smallest card in our catalogue that holds DistilProtBert is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 0.9 GB, and produces roughly 160 tokens per second. 818 cards in total can run it.

How fast is DistilProtBert on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 14,731 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 DistilProtBert clear that.

How much VRAM does DistilProtBert need?

About 0.9 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 DistilProtBert on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 0.9 GB and generating roughly 2,744 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