Multitask Unified Model (MUM)

Closed weights Google May 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
Google
Organisation type
Industry
Country
United States of America
Published
18 May 2021

What it does

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

Domain
Language, Multimodal, Vision
Task
Language modeling/generation, Image captioning, Question answering, Visual question answering, Translation, Character recognition (OCR), Search
Base model
T5-11B

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
tokens

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
Unknown

Sources

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

Reference
MUM: A new AI milestone for understanding information
Last updated
11 February 2026

What the numbers mean

Background

Multitask Unified Model (MUM) was published by Google, in the country recorded as United States of America, during May 2021. The category the publisher falls under is industry.

It works in the domain of Language, Multimodal, Vision, and is recorded as performing the task of language modeling/generation, Image captioning, Question answering, Visual question answering, Translation, Character recognition (OCR), Search.

Rather than being trained from scratch, it is derived from T5-11B. Most models at this scale are adapted from an existing base rather than built from nothing.

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

Answers

Multitask Unified Model (MUM) — common questions

01

Multitask Unified Model (MUM)— what is it used for?

It works in the domain of Language, Multimodal, Vision, and is recorded as handling the task of language modeling/generation, Image captioning, Question answering, Visual question answering, Translation, Character recognition (OCR), Search. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

02

Multitask Unified Model (MUM)— 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

Multitask Unified Model (MUM)— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

04

Multitask Unified Model (MUM)— 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

Multitask Unified Model (MUM)— who created it?

It was published by Google, based in United States of America, an organisation categorised as industry.

06

Multitask Unified Model (MUM)— when was it released?

It was published in May 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 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.