Perceiver IO (optical flow)

Closed weights DeepMind 27.9M parameters February 2020

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
8 February 2020
Authors
Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier Hénaff, Matthew M. Botvinick, Andrew Zisserman, Oriol Vinyals, João Carreira

What it does

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

Domain
Multimodal, Language, Vision
Task
Language modeling/generation, Image captioning

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
27.9M

Optical flow model (SOTA) was 27.9M params. There are other, larger models described in this paper, e.g. for language. "For the pixel- and patch-based models, total computational complexity for a forward pass on a 368 × 496 image is roughly 987 billion FLOPs, and there are roughly 27.9 million parameters."

Training data
146,022,400,000 tokens
Epochs
480

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.

Why it is tracked
SOTA improvement

"Perceiver IO... achieves state-of-the-art performance on Sintel optical flow estimation"

Record confidence
Confident
Citations
816

Sources

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

Reference
Perceiver IO: A General Architecture for Structured Inputs & Outputs
Last updated
25 May 2026

What the numbers mean

About this model

Perceiver IO (optical flow) was published by DeepMind, in United Kingdom of Great Britain and Northern Ireland, in February 2020. The organisation is categorised as industry.

It works in Multimodal, Language, Vision, and is recorded as doing language modeling/generation, Image captioning.

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

What went into building it

The training set ran to roughly 146,022,400,000 tokens.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

Perceiver IO (optical flow) — common questions

01

Is Perceiver IO (optical flow) open source?

No. Perceiver IO (optical flow) has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does Perceiver IO (optical flow) have?

Perceiver IO (optical flow) has 27.9M parameters. Optical flow model (SOTA) was 27.9M params. There are other, larger models described in this paper, e.g. for language. "For the pixel- and patch-based models, total computational complexity for a forward pass on a 368 × 496 image is roughly 987 billion FLOPs, and there are roughly 27.9 million 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.

03

Who created Perceiver IO (optical flow)?

Perceiver IO (optical flow) was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.

04

When was Perceiver IO (optical flow) released?

Perceiver IO (optical flow) was published in February 2020. 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 Perceiver IO (optical flow) used for?

Perceiver IO (optical flow) works in Multimodal, Language, Vision, and is recorded as handling language modeling/generation, Image captioning. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run Perceiver IO (optical flow)?

None. Perceiver IO (optical flow) 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.