Cloob

Closed weights Johannes Kepler University,HERE Technologies,Institute of Advanced Research in Artificial Intelligence October 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
Johannes Kepler University,HERE Technologies,Institute of Advanced Research in Artificial Intelligence
Organisation type
Academia,Academia
Country
Austria, Switzerland
Published
21 October 2021
Authors
Andreas Fürst ∗Elisabeth Rumetshofer ∗Johannes Lehner,Viet Tran,Fei Tang, Hubert Ramsauer, David Kreil, Michael Kopp, Günter Klambauer, Angela Bitto-Nemling, Sepp Hochreiter

What it does

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

Domain
Multimodal, Language, Vision
Task
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.

Training data
15,000,000 tokens

[Image-text pairs] "To be comparable to the CLIP results, we use the same subset of 15 million samples from the YFCC100M dataset"

How it is classified

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

Citations
127

Sources

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

Reference
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP
Last updated
25 May 2026

What the numbers mean

Background

Cloob was published by Johannes Kepler University,HERE Technologies,Institute of Advanced Research in Artificial Intelligence, in the country recorded as Austria, during October 2021. It comes out of an organisation categorised as academia,Academia.

It works in the domain of Multimodal, Language, Vision, and is recorded as performing the task of 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

It was trained on a corpus of about 15,000,000 tokens of text.

Answers

Cloob — common questions

01

Cloob— what is it used for?

It works in the domain of Multimodal, Language, Vision, and is recorded as handling the task of image captioning. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

Cloob— what GPU do I need to run it?

None. This 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

Cloob— is it open source?

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

04

Cloob— how many parameters does it have?

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

05

Cloob— who created it?

It was published by Johannes Kepler University,HERE Technologies,Institute of Advanced Research in Artificial Intelligence, based in Austria, an organisation categorised as academia,Academia.

06

Cloob— when was it released?

It was published in October 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.

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.