RT-2-X

Closed weights Google DeepMind 55B parameters October 2023

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
13 October 2023
Authors
Open X-Embodiment Collaboration

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-2

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

55B

Training data
tokens

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.

Why it is tracked
SOTA improvement

SOTA is claimed on Google Robot - Custom/internal evaluation "Emergent skills evaluation. To investigate the transfer of knowledge across robots, we conduct experiments with the Google Robot, assessing the performance on tasks like the ones shown in Fig. 5. These tasks involve objects and skills that are not present in the RT-2 dataset but occur in the Bridge dataset [95] for a different robot (the WidowX robot). Results are shown in Table II, Emergent Skills Evaluation column. Comparing rows (…

Record confidence
Confident
Citations
951

Sources

Where this record came from and when it was last checked.

Reference
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Last updated
25 May 2026

What the numbers mean

Where it came from

RT-2-X was published by Google DeepMind, in United States of America, in October 2023. industry is the category the publisher falls under.

It works in Robotics, and is recorded as doing robotic manipulation.

Its starting point was RT-2 — most models at this scale are adapted from an existing base rather than built from nothing.

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 is sOTA improvement.

Answers

RT-2-X — common questions

01

Who created RT-2-X?

RT-2-X was published by Google DeepMind, based in United States of America, categorised as industry.

02

When was RT-2-X released?

RT-2-X was published in October 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.

03

What is RT-2-X used for?

RT-2-X 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.

04

What GPU do I need to run RT-2-X?

None. RT-2-X 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.

05

Is RT-2-X open source?

No. RT-2-X has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does RT-2-X have?

RT-2-X has 55B parameters. 55B. 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.

Source

Original publication

Record last updated 25 May 2026

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.