PaLM-E
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,TU Berlin
- Organisation type
- Industry,Academia
- Country
- United States of America, Germany
- Published
- 6 March 2023
- Authors
- Danny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, Andy Zeng, Igor Mordatch, Pete Florence
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Robotics, Vision, Language
- Task
- Visual question answering, Robotic manipulation, Image captioning, Language generation
- Base model
- PaLM (540B)
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
- 562B
- Training data
- tokens
562B
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.
- Foundation model
- Yes
- Why it is tracked
- SOTA improvement
- Record confidence
- Likely
- Citations
- 2,645
"Our largest model, PaLM-E-562B with 562B parameters, in addition to being trained on robotics tasks, is a visual-language generalist with state-of-the-art performance on OK-VQA, and retains generalist language capabilities with increasing scale."
Sources
Where this record came from and when it was last checked.
- Reference
- PaLM-E: An Embodied Multimodal Language Model
- Last updated
- 25 May 2026
What the numbers mean
Background
PaLM-E was published by Google,TU Berlin, in United States of America, in March 2023. It comes out of industry,Academia.
It works in Robotics, Vision, Language, and is recorded as doing visual question answering, Robotic manipulation, Image captioning, Language generation.
It builds on PaLM (540B), which is why it shares that model's general shape and size.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
PaLM-E — common questions
When was PaLM-E released?
PaLM-E was published in March 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 PaLM-E used for?
PaLM-E works in Robotics, Vision, Language, and is recorded as handling visual question answering, Robotic manipulation, Image captioning, Language generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run PaLM-E?
None. PaLM-E 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 PaLM-E open source?
No. PaLM-E has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does PaLM-E have?
PaLM-E has 562B parameters. 562B. 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 PaLM-E?
PaLM-E was published by Google,TU Berlin, based in United States of America, categorised as industry,Academia.
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.