GAIA-1
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
- Wayve
- Organisation type
- Industry
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 29 September 2023
- Authors
- Anthony Hu, Lloyd Russell, Hudson Yeo, Zak Murez, George Fedoseev, Alex Kendall, Jamie Shotton, Gianluca Corrado
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Video, Vision, Multimodal, Language
- Task
- Self-driving car, Video generation, Instruction interpretation
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
- 9B
- Training data
- tokens
9B "GAIA-1’s world model has 6.5 billion parameters" "GAIA-1’s video decoder has 2.6 billion parameters"
"Our training dataset consists of 4,700 hours at 25Hz of proprietary driving data collected in London, UK between 2019 and 2023. This corresponds to approximately 420M unique images"
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
- 1.2 × 10²² FLOP
- How it was established
- Hardware,Reported
312000000000000 FLOP / GPU / sec [A100 reported, bf16 assumed] * 34560 GPU-hours [see training time notes] * 3600 sec/ hour * 0.3 [assumed utilization] = 1.1645338e+22 FLOP they also report compute of ~1*10^22 via a graph here: https://wayve.ai/thinking/scaling-gaia-1/
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
- NVIDIA A100
- Chip-hours
- 34,560
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
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- GAIA-1: A Generative World Model for Autonomous Driving
- Last updated
- 28 November 2025
What the numbers mean
About this model
GAIA-1 was published by Wayve, in United Kingdom of Great Britain and Northern Ireland, in September 2023. It comes out of industry.
It works in Video, Vision, Multimodal, Language, and is recorded as doing self-driving car, Video generation, Instruction interpretation.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training run consumed about 1.2 × 10²² FLOP, on NVIDIA A100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Answers
GAIA-1 — common questions
Is GAIA-1 open source?
No. GAIA-1 has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does GAIA-1 have?
GAIA-1 has 9B parameters. 9B "GAIA-1’s world model has 6.5 billion parameters" "GAIA-1’s video decoder has 2.6 billion 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.
Who created GAIA-1?
GAIA-1 was published by Wayve, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.
When was GAIA-1 released?
GAIA-1 was published in September 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is GAIA-1 used for?
GAIA-1 works in Video, Vision, Multimodal, Language, and is recorded as handling self-driving car, Video generation, Instruction interpretation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train GAIA-1?
Around 1.2 × 10²² FLOP, on NVIDIA A100. 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.
What GPU do I need to run GAIA-1?
None. GAIA-1 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.
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.