RT-2
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
- 28 July 2023
- Authors
- Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski, Tianli Ding, Danny Driess, Avinava Dubey, Chelsea Finn, Pete Florence, Chuyuan Fu, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Kehang Han, Karol Hausman, Alexander Herzog, Jasmine Hsu, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Isabel Leal, Lisa Lee, Tsan…
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
- PaLI-X
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
- 55B
- Training data
- tokens
"We train two specific instantiations of RT-2 that leverage pre-trained VLMs: (1) RT-2-PaLI-X is built from 5B and 55B PaLI-X (Chen et al., 2023a), and (2) RT-2-PaLM-E is built from 12B PaLM-E (Driess et al., 2023)." 55B and 12B have similar overall performance
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
no model weights or training code releases are mentioned https://robotics-transformer2.github.io/
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Foundation model
- Yes
- Why it is tracked
- SOTA improvement
- Record confidence
- Confident
- Citations
- 3,009
"We compare our method to multiple state-of-the-art baselines that challenge different aspects of our method. All of the baselines use the exact same robotic data... Here, on average, both instantiations of RT-2 perform similarly, resulting in ∼2x improvement over the next two baselines, RT-1 and MOO, and ∼6x better than the other baselines" Top10 recent paper from Sebastian Sartor 2025-05-14
Sources
Where this record came from and when it was last checked.
- Reference
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
RT-2 was published by Google DeepMind, in the country recorded as United States of America, during July 2023. It comes out of an organisation categorised as industry.
It works in the domain of Robotics, and is recorded as performing the task of robotic manipulation.
Rather than being trained from scratch, it is derived from PaLI-X. That is the usual way a specialised model is produced.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Its inclusion criterion: sOTA improvement.
Answers
RT-2 — common questions
RT-2— 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.
RT-2— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
RT-2— how many parameters does it have?
It has a parameter count of 55B. "We train two specific instantiations of RT-2 that leverage pre-trained VLMs: (1) RT-2-PaLI-X is built from 5B and 55B PaLI-X (Chen et al., 2023a), and (2) RT-2-PaLM-E is built from 12B PaLM-E (Driess et al., 2023)." 55B and 12B have similar overall performance. 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.
RT-2— who created it?
It was published by Google DeepMind, based in United States of America, an organisation categorised as industry.
RT-2— when was it released?
It was published in July 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.
RT-2— what is it used for?
It works in the domain of Robotics, and is recorded as handling the task of robotic manipulation. 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.