ProteinStructureTransformer

Closed weights Max Planck Institute of Biochemistry 1.1B parameters January 2024

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

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
Max Planck Institute of Biochemistry
Organisation type
Academia
Country
Germany
Published
26 January 2024
Authors
Dexiong Chen, Philip Hartout, Paolo Pellizzoni, Carlos Oliver, Karsten Borgwardt

What it does

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

Domain
Biology
Task
Protein or nucleotide language model (pLM/nLM)
Base model
ESM2-650M

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
1.1B
Training data
tokens

542,378 proteins × 300 residues/protein = 162,713,400 tokens (1.627e8) Final estimate: 1.6e8 datapoints

Epochs
100

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
7.6 × 10²¹ FLOP

GPU hour estimate 4*36000s*9.9e+14*0.4=5.7e+19 Base model: 7.560000000001e+21 Combined: 7616995200001001000000

How it was established
Hardware
Fine-tuning compute
5.7 × 10¹⁹ FLOP

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 H100 SXM5 80GB
Chips used
4
Wall-clock time
10 hours
Power draw
5.5 kW

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
21

Sources

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

Reference
ENDOWING PROTEIN LANGUAGE MODELS WITH STRUCTURAL KNOWLEDGE
Last updated
25 May 2026

What the numbers mean

Background

ProteinStructureTransformer was published by Max Planck Institute of Biochemistry, in the country recorded as Germany, during January 2024. It comes out of an organisation categorised as academia.

It works in the domain of Biology, and is recorded as performing the task of protein or nucleotide language model (pLM/nLM).

Rather than being trained from scratch, it is derived from ESM2-650M. That is why it shares the base model's general shape and size.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

Producing it required arithmetic totalling around 7.6 × 10²¹ FLOP, on hardware recorded as NVIDIA H100 SXM5 80GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

ProteinStructureTransformer — common questions

01

ProteinStructureTransformer— how many parameters does it have?

It has a parameter count of 1.1B. 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.

02

ProteinStructureTransformer— who created it?

It was published by Max Planck Institute of Biochemistry, based in Germany, an organisation categorised as academia.

03

ProteinStructureTransformer— when was it released?

It was published in January 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

ProteinStructureTransformer— what is it used for?

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

05

ProteinStructureTransformer— how much compute was used to train it?

Training consumed around 7.6 × 10²¹ FLOP, on hardware recorded as NVIDIA H100 SXM5 80GB. 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.

06

ProteinStructureTransformer— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

07

ProteinStructureTransformer— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

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.