π0.7 (pi-0.7)

Closed weights Physical Intelligence 5.3B parameters April 2026

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
Physical Intelligence
Organisation type
Industry
Country
United States of America
Published
16 April 2026
Authors
Bo Ai, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Greg Balke, Kevin Black, George Bokinsky, Shihao Cao, Thomas Charbonnier, Vedant Choudhary, Foster Collins, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Maitrayee Dhaka, Jared DiCarlo, Danny Driess, Michael Equi, Adnan Esmail, Yunhao Fang, Chelsea Finn, Catherine Glossop, Thomas Godden, Ivan Goryachev, Lachlan Groom, Haroun Hab…

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Robotics, Vision
Task
Robotic manipulation

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
5.3B

"nitialized from the Gemma3 4B-parameter VLM [106] [...] (including a 400M-parameter vision encoder), and a flow matching action expert with 860M parameters. The model has about 5B total parameters."

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

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

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

Reference
π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
Last updated
13 May 2026

What the numbers mean

About this model

π0.7 (pi-0.7) was published by Physical Intelligence, in United States of America, in April 2026. industry is the category the publisher falls under.

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

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Answers

π0.7 (pi-0.7) — common questions

01

Who created π0.7 (pi-0.7)?

π0.7 (pi-0.7) was published by Physical Intelligence, based in United States of America, categorised as industry.

02

When was π0.7 (pi-0.7) released?

π0.7 (pi-0.7) was published in April 2026.

03

What is π0.7 (pi-0.7) used for?

π0.7 (pi-0.7) works in Robotics, Vision, 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 π0.7 (pi-0.7)?

None. π0.7 (pi-0.7) 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 π0.7 (pi-0.7) open source?

No. π0.7 (pi-0.7) has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does π0.7 (pi-0.7) have?

π0.7 (pi-0.7) has 5.3B parameters. "nitialized from the Gemma3 4B-parameter VLM [106] [...] (including a 400M-parameter vision encoder), and a flow matching action expert with 860M parameters. The model has about 5B total parameters.". 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 13 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.