GearNet

Closed weights Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,University of Cambridge,IBM Research,HEC Montreal,CIFAR AI Research November 2022

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,University of Cambridge,IBM Research,HEC Montreal,CIFAR AI Research
Organisation type
Academia,Academia,Academia,Industry,Academia,Research collective
Country
Canada, United Kingdom of Great Britain and Northern Ireland, United States of America
Published
1 November 2022
Authors
Zuobai Zhang, Minghao Xu, Arian Jamasb, Vijil Chenthamarakshan, Aurélie Lozano, Payel Das, Jian Tang

What it does

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

Domain
Biology
Task
Proteins, Protein function prediction, Protein fold classification

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
805,000 tokens

805,000 proteins × 300 residues/protein = 241,500,000 datapoints (2.415 × 10^8) Breakdown: 1. Initial protein count: 365,000 + 440,000 = 805,000 2. Final calculation: 805,000 × 300 = 241,500,000

Epochs
50

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
4
Power draw
3.2 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
312

Sources

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

Reference
Protein Representation Learning by Geometric Structure Pretraining
Last updated
25 May 2026

What the numbers mean

About this model

GearNet was published by Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),University of Montreal / Université de Montréal,University of Cambridge,IBM Research,HEC Montreal,CIFAR AI Research, in Canada, in November 2022. The organisation is categorised as academia,Academia,Academia,Industry,Academia,Research collective.

It works in Biology, and is recorded as doing proteins, Protein function prediction, Protein fold classification.

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

What went into building it

Around 805,000 tokens went into training it.

Answers

GearNet — common questions

01

How many parameters does GearNet have?

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

02

Who created GearNet?

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

03

When was GearNet released?

GearNet was published in November 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.

04

What is GearNet used for?

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

05

What GPU do I need to run GearNet?

None. GearNet 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 GearNet open source?

The licensing for GearNet 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.