RT-2

Google DeepMind, US · July 2023

Foundation VLAClosed weightsAlso written Robotics Transformer 2, RT-2-PaLI-X, RT-2-PaLM-E
Parameters
55 B
The headline model RT-2-PaLI-X-55B has 55B parameters.
GPU memory
102 GB
weights at bf16, computed
Inference latency
not published
per action step
Weights
closed
no public checkpoint

What it is

RT-2 is the model that defined the term vision-language-action. It co-fine-tunes a large VLM (PaLI-X at 5B and 55B, or PaLM-E at 12B) on robot trajectories and internet VQA data by writing actions as text tokens in the same vocabulary. The payoff is semantic: about 3x on emergent skills such as symbol understanding and reasoning, and roughly 2x generalization to unseen objects and environments. The cost is deployment, since the 55B model only reaches 1 to 3 Hz served from a multi-TPU cloud service, and nothing was ever released. Treat it as a reference point in the literature, not as something you can run.

Architecture

Backbone
Two instantiations: PaLI-X (5B and 55B) and PaLM-E (12B), co-fine-tuned on robot trajectories and internet vision-language data.
Action head
Actions expressed as text tokens. Each action dimension is emitted autoregressively as a string in the same vocabulary as natural language, which is what allows co-fine-tuning with VQA data.
Parameters
The headline model RT-2-PaLI-X-55B has 55B parameters. The paper also evaluates RT-2-PaLI-X-5B, RT-2-PaLM-E-12B and a PaLI-3B variant used for the simulated Language-Table experiments. No weights of any size were released.
Pretraining data
Web-scale vision-language pretraining inherited from PaLI-X and PaLM-E, co-fine-tuned with the RT-1 robot demonstration dataset (over 130k episodes on the Everyday Robots mobile manipulator).
Embodiments
Everyday Robots mobile manipulator (single arm plus mobile base)

What hardware it needs

This is the section most people came for, so it is worth being precise about which numbers are measured and which are arithmetic.

Computed from 55 B parameters. Weights only, so treat it as a floor: activations, image encoder intermediates and the CUDA context come on top, in practice 30 to 50 percent more for inference.
PrecisionWeightsNote
fp32205 GBTraining master weights, rarely used for inference
bf16 or fp16102 GBThe usual way these checkpoints are served
int851 GBQuantised, expect some loss of precision on fine motions
int426 GBAggressive quantisation, verify success rate before trusting it

The authors publish no memory or latency figure for this model. Everything above is computed from the parameter count.

Reported results

Grouped by what the evaluation actually asked. Values from different suites are not comparable with each other, so each one keeps its suite and split.

Simulation

Reproducible benchmark suites. Everyone runs the same episodes, so the numbers can be compared inside a suite.

  • Language-Table (simulation) held-out simulated tasks
    90%
    success rateRT-2-PaLI-3B variant, reported as 90 +/- 10. Same table lists RT-1 at 74 +/- 13 and LAVA at 77 +/- 4.source

Real world

Rollouts on physical hardware. The setups differ, so read these as evidence, not as a ranking.

  • RT-2 emergent skills evaluation symbol understanding, reasoning and human recognition
    3 x
    improvement over RT-1 baselineAuthors' own evaluation across roughly 6k evaluation trials.source
  • RT-2 generalization evaluation unseen objects, backgrounds and environments
    2 x
    improvement over baselinesStated by the authors as approximately 2x, no exact per-category table on the project page.source

Fine tuned tasks

No results in this category are published for this model.

On real hardware

Evaluated on the Everyday Robots mobile manipulator across roughly 6k real evaluation trials. The demonstrated wins are semantic rather than dexterous: interpreting commands absent from robot data, picking by relative size or proximity, and chain-of-thought selection of an improvised tool.

Fine tuning it yourself

Not possible outside Google. No weights, no code and no serving stack were published.

Where it helps, where it does not

Strengths

  • First model to show that web-scale VLM knowledge transfers directly into robot action, roughly 3x on emergent skills
  • Chain-of-thought prompting enables multi-stage semantic reasoning before acting
  • Actions as text tokens is a simple recipe that most later VLAs build on

Limits

  • Weights, code and checkpoints were never released, so it cannot be reproduced or deployed
  • Requires a multi-TPU cloud service, which rules out offline or latency-critical use
  • 1 to 3 Hz for the 55B model is too slow for reactive control
  • Single embodiment only, and the paper reports no new dexterous skills beyond what the robot data already contained
  • No parameter-efficient or consumer-GPU path exists at 55B

Sources

Everything on this page was taken from these documents. Where they disagree with what you read here, they win.

Entry last checked 2026-08-11.

Try a policy on a real arm

A physical SO-100 is online and free to drive in the browser, and five of the models in this arena can be fine tuned on a dataset you record with your own.