GameNGen
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 Research,Google DeepMind,Tel Aviv University
- Organisation type
- Industry,Industry,Academia
- Country
- United States of America, Israel
- Published
- 22 August 2024
- Authors
- Dani Valevski, Yaniv Leviathan, Moab Arar, Shlomi Fruchter
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Games
- Task
- Doom
- Base model
- Stable Diffusion (LDM-KL-8-G)
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
- 458,802,000,000 tokens
" We use a batch size of 128 " (for the main training) "Unless noted otherwise, all results in the paperare after 700,000 training steps. <..> We use a batch size of 2,048 for optimizing the latent decoder, other training parameters are identical to those of the denoiser. <..> Overall we generate 900M frames for training. All image frames (during training, inference, and conditioning) are at a resolution of 320x240 padded to 320x256."
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 v5e
- Chips used
- 128
- Power draw
- 56.8 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
- Unknown
Sources
Where this record came from and when it was last checked.
- Reference
- Diffusion Models Are Real-Time Game Engines
- Last updated
- 28 November 2025
What the numbers mean
About this model
GameNGen was published by Google Research,Google DeepMind,Tel Aviv University, in the country recorded as United States of America, during August 2024. The publishing organisation is categorised as industry,Industry,Academia.
It works in the domain of Games, and is recorded as performing the task of doom.
Rather than being trained from scratch, it is derived from Stable Diffusion (LDM-KL-8-G). That is the usual way a specialised model is produced.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
It was trained on a corpus of about 458,802,000,000 tokens of text.
Answers
GameNGen — common questions
GameNGen— 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.
GameNGen— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
GameNGen— 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.
GameNGen— who created it?
It was published by Google Research,Google DeepMind,Tel Aviv University, based in United States of America, an organisation categorised as industry,Industry,Academia.
GameNGen— when was it released?
It was published in August 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.
GameNGen— what is it used for?
It works in the domain of Games, and is recorded as handling the task of doom. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.