Protst

Closed weights Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,Intel Labs,HEC Montreal,CIFAR AI Research January 2023

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
Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,Intel Labs,HEC Montreal,CIFAR AI Research
Organisation type
Academia,Academia,Industry,Academia,Research collective
Country
Canada, United States of America
Published
28 January 2023
Authors
Minghao Xu, Xinyu Yuan, Santiago Miret, Jian Tang

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.

Training data
tokens

Total Datapoints = (553,052 pairs × 450 residues/pair) + (553,052 pairs × 50 tokens/pair) = 248,873,400 + 27,652,600 = 276,526,000 (2.765e+8)

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
1.4 × 10¹⁹ FLOP

1. Hardware setup: 4x NVIDIA Tesla V100 GPUs (1.30 x 10^14 FLOP/s per GPU) 2. Training duration: 69,131 seconds (≈19.2 hours) - estimated from 20 epochs, 553,052 samples, batch size 16, assuming 0.1s per step 3. Utilization rate: 40% 4. Final calculation: 1.30 x 10^14 FLOP/s × 4 GPUs × 69,131s × 0.4 = 1.44 x 10^19 FLOPs

How it was established
Hardware

How it is classified

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

Record confidence
Likely
Citations
124

Sources

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

Reference
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
Last updated
1 January 2026

What the numbers mean

What this model is

Protst was published by Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,Intel Labs,HEC Montreal,CIFAR AI Research, in Canada, in January 2023. The organisation is categorised as academia,Academia,Industry,Academia,Research collective.

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

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

Training and provenance

The training run consumed about 1.4 × 10¹⁹ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Answers

Protst — common questions

01

When was Protst released?

Protst 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.

02

What is Protst used for?

Protst works in Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

How much compute was used to train Protst?

Around 1.4 × 10¹⁹ FLOP. 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.

04

What GPU do I need to run Protst?

None. Protst 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.

05

Is Protst open source?

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

06

How many parameters does Protst have?

No parameter count has been published for Protst, which is why no memory or speed figure appears on this page.

07

Who created Protst?

Protst was published by Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,Intel Labs,HEC Montreal,CIFAR AI Research, based in Canada, categorised as academia,Academia,Industry,Academia,Research collective.

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.