RT-1 + AutoRT
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
- 4 January 2024
- Authors
- Michael Ahn, Debidatta Dwibedi, Chelsea Finn, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Karol Hausman, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, Sean Kirmani, Isabel Leal, Edward Lee, Sergey Levine, Yao Lu, Isabel Leal, Sharath Maddineni, Kanishka Rao, Dorsa Sadigh, Pannag Sanketi, Pierre Sermanet, Quan Vuong, Stefan Welker, Fei Xia, Ted Xiao, Peng Xu, Steve Xu, Zhuo Xu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Robotics
- Task
- Robotic manipulation
- Base model
- RT-1
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
- 35M
- Training data
- 207,000 tokens
from RT-1
"Data statistics: In total, 53 robots were used to collect 77,000 new episodes over the course of 7 months, with a peak load of over 20 simultaneous robots. Over 6,650 unique instructions appear in the dataset"
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
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents
- Last updated
- 28 November 2025
What the numbers mean
Background
RT-1 + AutoRT was published by Google DeepMind, in United States of America, in January 2024. The organisation is categorised as industry.
It works in Robotics, and is recorded as doing robotic manipulation.
It builds on RT-1, which is why it shares that model's general shape and size.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
Around 207,000 tokens went into training it.
Answers
RT-1 + AutoRT — common questions
What is RT-1 + AutoRT used for?
RT-1 + AutoRT works in Robotics, and is recorded as handling robotic manipulation. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run RT-1 + AutoRT?
None. RT-1 + AutoRT 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.
Is RT-1 + AutoRT open source?
No. RT-1 + AutoRT has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does RT-1 + AutoRT have?
RT-1 + AutoRT has 35M parameters. from RT-1. 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 RT-1 + AutoRT?
RT-1 + AutoRT was published by Google DeepMind, based in United States of America, categorised as industry.
When was RT-1 + AutoRT released?
RT-1 + AutoRT was published in January 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.
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.