Big Transfer (BiT-M)

Closed weights Google Brain 928M parameters December 2019

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
Google Brain
Organisation type
Industry
Country
United States of America
Published
24 December 2019
Authors
Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby

What it does

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

Domain
Vision
Task
Image 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.

Parameters
928M

"928 million" stated directly in paper

Training data
14,200,000 tokens

"We train both BiT-S and BiT-M for 90 epochs"

Epochs
90

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
Google TPU v3

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
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

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
1,361

Sources

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

Reference
Big Transfer (BiT): General Visual Representation Learning
Last updated
25 May 2026

What the numbers mean

Where it came from

Big Transfer (BiT-M) was published by Google Brain, in United States of America, in December 2019. It comes out of industry.

It works in Vision, and is recorded as doing image classification.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

What went into building it

The training set ran to roughly 14,200,000 tokens.

Answers

Big Transfer (BiT-M) — common questions

01

Is Big Transfer (BiT-M) open source?

No. Big Transfer (BiT-M) has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does Big Transfer (BiT-M) have?

Big Transfer (BiT-M) has 928M parameters. "928 million" stated directly in paper. 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.

03

Who created Big Transfer (BiT-M)?

Big Transfer (BiT-M) was published by Google Brain, based in United States of America, categorised as industry.

04

When was Big Transfer (BiT-M) released?

Big Transfer (BiT-M) was published in December 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Big Transfer (BiT-M) used for?

Big Transfer (BiT-M) works in Vision, and is recorded as handling image classification. 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.

06

What GPU do I need to run Big Transfer (BiT-M)?

None. Big Transfer (BiT-M) 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.

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.