ProstT5

Closed weights Technical University of Munich,Seoul National University,Institute for Advanced Study,TUM School of Life Sciences Weihenstephan 3B parameters March 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
Technical University of Munich,Seoul National University,Institute for Advanced Study,TUM School of Life Sciences Weihenstephan
Organisation type
Academia,Academia,Academia,Academia
Country
Germany, Korea (Republic of), United States of America
Published
24 March 2024
Authors
Michael Heinzinger, Konstantin Weissenow, Joaquin Gomez Sanchez, Adrian Henkel, Milot Mirdita, Martin Steinegger, Burkhard Rost

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)

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

Number of samples = 34M Tokens per sequence = 238 Total = 34,000,000 × 238 = 8,092,000,000 tokens ≈ 8.1B

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
3.1 × 10²¹ FLOP

1. Hardware setup: 8x NVIDIA A100 GPUs (3.12e14 FLOP/s per GPU) 2. Training duration: Directly provided - 36 days total (10 days pre-training + 26 days translation training) = 3,110,400 seconds 3. Utilization rate: 40% 4. Final calculation: 3.12e14 FLOP/s × 8 GPUs × 3,110,400s × 0.4 = 3.1e21 FLOPs

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 A100
Chips used
8
Wall-clock time
864 hours (36 days)
Power draw
6.3 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
212

Sources

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

Reference
Bilingual Language Model for Protein Sequence and Structure
Last updated
1 January 2026

What the numbers mean

Where it came from

ProstT5 was published by Technical University of Munich,Seoul National University,Institute for Advanced Study,TUM School of Life Sciences Weihenstephan, in Germany, in March 2024. The organisation is categorised as academia,Academia,Academia,Academia.

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

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

The training run consumed about 3.1 × 10²¹ FLOP, on NVIDIA A100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Answers

ProstT5 — common questions

01

Who created ProstT5?

ProstT5 was published by Technical University of Munich,Seoul National University,Institute for Advanced Study,TUM School of Life Sciences Weihenstephan, based in Germany, categorised as academia,Academia,Academia,Academia.

02

When was ProstT5 released?

ProstT5 was published in March 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.

03

What is ProstT5 used for?

ProstT5 works in Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM). A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

04

How much compute was used to train ProstT5?

Around 3.1 × 10²¹ FLOP, on NVIDIA A100. 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.

05

What GPU do I need to run ProstT5?

None. ProstT5 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.

06

Is ProstT5 open source?

The licensing for ProstT5 was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

07

How many parameters does ProstT5 have?

ProstT5 has 3B 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.

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.