Genie

Closed weights Google DeepMind 10.7B parameters February 2024

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 DeepMind
Organisation type
Industry
Country
United States of America
Published
23 February 2024
Authors
Jake Bruce, Michael Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, Yusuf Aytar, Sarah Bechtle, Feryal Behbahani, Stephanie Chan, Nicolas Heess, Lucy Gonzalez, Simon Osindero, Sherjil Ozair, Scott Reed, Jingwei Zhang, Konrad Zolna, Jeff Clune, Nando de Freitas, Satinder Singh, Tim Rocktäschel

What it does

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

Domain
Video, Games
Task
Video generation, Image-to-video, Text-to-video

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
10.7B

When combined with the tokenizer and action model this brings the total to 10.7B parameters, trained on 942B tokens, which we refer to as the Genie model.

Training data
942,000,000,000 tokens

When combined with the tokenizer and action model this brings the total to 10.7B parameters, trained on 942B tokens, which we refer to as the Genie model.

Batch size
512

As a result, for our final model, we train a 10.1B dynamics model with a batch size of 512, for a total of 125k steps, using 256 TPUv5p

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
6.6 × 10²² FLOP

Table 12

How it was established
Reported

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 v5p
Chips used
256
Power draw
273.6 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

We have chosen not to release the trained model checkpoints, the model’s training dataset, or examples from that data to accompany this paper or the website. We would like to have the opportunity to further engage with the research (and video game) community and to ensure that any future such releases are respectful, safe and responsible.

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
Genie: Generative Interactive Environments
Last updated
28 November 2025

What the numbers mean

Background

Genie was published by Google DeepMind, in the country recorded as United States of America, during February 2024. It comes out of an organisation categorised as industry.

It works in the domain of Video, Games, and is recorded as performing the task of video generation, Image-to-video, Text-to-video.

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

Training and provenance

Producing it required arithmetic totalling around 6.6 × 10²² FLOP, on hardware recorded as Google TPU v5p. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 942,000,000,000 tokens of text.

Answers

Genie — common questions

01

Genie— is it open source?

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

02

Genie— how many parameters does it have?

It has a parameter count of 10.7B. When combined with the tokenizer and action model this brings the total to 10.7B parameters, trained on 942B tokens, which we refer to as the Genie model. 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

Genie— who created it?

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

04

Genie— when was it released?

It was published in February 2024. 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

Genie— what is it used for?

It works in the domain of Video, Games, and is recorded as handling the task of video generation, Image-to-video, Text-to-video. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

Genie— how much compute was used to train it?

Training consumed around 6.6 × 10²² FLOP, on hardware recorded as Google TPU v5p. 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.

07

Genie— 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.

Source

Original publication

Record last updated 28 November 2025

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.