DCTransformer (ImageNet)

Closed weights DeepMind 736M parameters March 2021

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
DeepMind
Organisation type
Industry
Country
United Kingdom of Great Britain and Northern Ireland
Published
5 March 2021
Authors
Charlie Nash, Jacob Menick, Sander Dieleman, Peter W. Battaglia

What it does

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

Domain
Image generation
Task
Image generation

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
736M

parameters (Table 3): 738e6

Training data
1,000,000,000,000 tokens

[tokens] Table 3: Image resolution 384 batch size: 512 tokens processed: 1000e9 " We use a target chunk size of 896 in all our experiments"

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
4.4 × 10²¹ FLOP

6 FLOP / token / parameter * 738 * 10^6 parameters * 1000 * 10^9 tokens = 4.428e+21 FLOP

How it was established
Operation counting

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
Chips used
128
Power draw
116.8 kW

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

Sources

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

Reference
Generating Images with Sparse Representations
Last updated
11 February 2026

What the numbers mean

Where it came from

DCTransformer (ImageNet) was published by DeepMind, in United Kingdom of Great Britain and Northern Ireland, in March 2021. It comes out of industry.

It works in Image generation, and is recorded as doing image generation.

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

How it was trained

Producing it required around 4.4 × 10²¹ FLOP of arithmetic, on Google TPU v3, which is a statement about the training budget rather than about inference.

It was trained on about 1,000,000,000,000 tokens of text.

Answers

DCTransformer (ImageNet) — common questions

01

How much compute was used to train DCTransformer (ImageNet)?

Around 4.4 × 10²¹ FLOP, on Google TPU v3. 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.

02

What GPU do I need to run DCTransformer (ImageNet)?

None. DCTransformer (ImageNet) 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.

03

Is DCTransformer (ImageNet) open source?

No. DCTransformer (ImageNet) has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does DCTransformer (ImageNet) have?

DCTransformer (ImageNet) has 736M parameters. parameters (Table 3): 738e6. 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.

05

Who created DCTransformer (ImageNet)?

DCTransformer (ImageNet) was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.

06

When was DCTransformer (ImageNet) released?

DCTransformer (ImageNet) was published in March 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

What is DCTransformer (ImageNet) used for?

DCTransformer (ImageNet) works in Image generation, and is recorded as handling image generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 11 February 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.