ProteinLM TPS calculator

Open weights Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,Tencent 3B parameters August 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 · Q6_K · 17.9 tok/s

Fastest card

B200

1,129 tok/s · 180 GB

Which GPUs can run ProteinLM?

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
1,129 tok/s 678–1,807 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	3.9 GB	Q8_0	Comfortable
1,129 tok/s 678–1,807 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	3.9 GB	Q8_0	Comfortable
902 tok/s 541–1,443 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
902 tok/s 541–1,443 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	3.9 GB	Q8_0	Comfortable
721 tok/s 433–1,154 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
690 tok/s 414–1,105 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
690 tok/s 414–1,105 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	3.9 GB	Q8_0	Comfortable
661 tok/s 396–1,057 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
586 tok/s 352–938 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	3.9 GB	Q8_0	Comfortable
556 tok/s 334–890 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
474 tok/s 285–759 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	3.9 GB	Q8_0	Comfortable
361 tok/s 217–578 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
361 tok/s 217–578 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	3.9 GB	Q8_0	Comfortable
301 tok/s 181–482 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
295 tok/s 177–471 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	3.9 GB	Q8_0	Comfortable
288 tok/s 173–461 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	3.9 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: Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,Tencent
Organisation type: Academia,Academia,Industry
Country: China
Published: 17 August 2021
Authors: Yijia Xiao, Jiezhong Qiu, Ziang Li, Chang-Yu Hsieh, Jie Tang

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)
Approach: Self-supervised learning

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: 3B
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: 1.6 × 10²² 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 V100
Chips used: 48
Chip-hours: 12,096
Wall-clock time: 252 hours (10.5 days)
Power draw: 29.1 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: 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: Confident
Citations: 40

Sources

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

Reference: Modeling Protein Using Large-scale Pretrain Language Model
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run ProteinLM

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 ProteinLM

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

3.2 GB

Fastest

1,129 tok/s

ProteinLM is small enough at 3B 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 Q6_K, for about 17.9 tokens per second.

Top of the range is the B200, at roughly 1,129 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

ProteinLM was published by Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,Tencent, in China, in August 2021. academia,Academia,Industry is the category the publisher falls under.

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

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all.

Reading the throughput figures

Half the cards that hold it manage more than 35.8 tokens per second, and 780 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.

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 1.6 × 10²² FLOP, on NVIDIA V100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Step by step

How to choose a GPU for ProteinLM

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

Every card here has been checked against ProteinLM — around 3.2 GB at Q6_K. Capacity is the gate — a card either holds it or it does not.
02

Match the context to your actual use

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for ProteinLM.
03

Choose how far you will compress it

Each card runs the least-compressed copy it can hold — Q6_K on the smallest card that fits. Setting a floor drops the cards that only manage ProteinLM by squeezing it further than you would want.
04

Compare tokens per second, not specifications

Ranking by tokens per second for ProteinLM follows memory bandwidth, not core counts, which is why the B200 tops it at 1,129 tok/s.
05

Check the fit verdict before buying

Tight means ProteinLM 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

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

Answers

ProteinLM — common questions

Can I run ProteinLM on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 3.9 GB and generating roughly 160 tokens per second — a comfortable fit.

Can I run ProteinLM on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 3.9 GB and generating roughly 189 tokens per second — a comfortable fit.

Is ProteinLM open source?

Its weights are published, so ProteinLM 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 ProteinLM have?

ProteinLM has 3B parameters. "We have trained multiple largescale models on the PFAM[7] dataset, the largest with 3 billion 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 ProteinLM?

ProteinLM was published by Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI,Tencent, based in China, categorised as academia,Academia,Industry.

When was ProteinLM released?

ProteinLM was published in August 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.

What is ProteinLM used for?

ProteinLM works in Biology, and is recorded as handling proteins, Protein or nucleotide language model (pLM/nLM). These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download ProteinLM?

The weights for ProteinLM 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 ProteinLM?

Around 1.6 × 10²² FLOP, on NVIDIA V100. 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 ProteinLM if it does not fit in my GPU?

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

Would two GPUs run ProteinLM faster?

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

Why does the quantisation differ between cards for ProteinLM?

Because capacity varies, so does how hard ProteinLM has to be squeezed — 2 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these ProteinLM 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 678–1,807 tok/s on the B200 rather than a single number.

What GPU do I need to run ProteinLM?

The smallest card in our catalogue that holds ProteinLM is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.2 GB, and produces roughly 17.9 tokens per second. 818 cards in total can run it.

How fast is ProteinLM on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,129 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 780 of the cards that can run ProteinLM clear that.

How much VRAM does ProteinLM need?

About 3.2 GB at Q6_K 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 ProteinLM on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 3.9 GB and generating roughly 210 tokens per second — a comfortable fit.

Can I run ProteinLM on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 3.9 GB and generating roughly 129 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