π0.6 (pi-0.6)
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
- 17 November 2025
- Authors
- Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Jared DiCarlo, Danny Driess, Michael Equi, Adnan Esmail, Yunhao Fang, Chelsea Finn, Catherine Glossop, Thomas Godden, Ivan Goryachev, Lachy Groom, Hunter Hancock, Karol Hausman, Gashon Hussein, Brian Ichter, Szymon Jakubczak, Rowan Jen, Tim Jones, Ben Katz, Liyiming Ke, Chandra…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Robotics, Vision
- Task
- Robotic manipulation
- Base model
- Gemma 3 4B
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
- Training data
- tokens
"(ii) The base VLM is Gemma 3 [78] 4B model. (iii) The size of the action expert is increased to 860M parameters." Model card (https://website.pi-asset.com/pi06star/PI06_model_card.pdf) notes in Figure 1 that the VLM also includes SigLIP (400M).
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.
- Why it is tracked
- Discretionary
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- π∗0.6: a VLA That Learns From Experience
- Last updated
- 7 May 2026
What the numbers mean
About this model
π0.6 (pi-0.6) was published by Physical Intelligence, in United States of America, in November 2025. The organisation is categorised as industry.
It works in Robotics, Vision, and is recorded as doing robotic manipulation.
It is derived from Gemma 3 4B rather than trained from scratch, which 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.
What went into building it
The reason it appears in this catalogue at all is discretionary.
Answers
π0.6 (pi-0.6) — common questions
How many parameters does π0.6 (pi-0.6) have?
π0.6 (pi-0.6) has 5.3B parameters. "(ii) The base VLM is Gemma 3 [78] 4B model. (iii) The size of the action expert is increased to 860M parameters." Model card (https://website.pi-asset.com/pi06star/PI06_model_card.pdf) notes in Figure 1 that the VLM also includes SigLIP (400M). 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 π0.6 (pi-0.6)?
π0.6 (pi-0.6) was published by Physical Intelligence, based in United States of America, categorised as industry.
When was π0.6 (pi-0.6) released?
π0.6 (pi-0.6) was published in November 2025.
What is π0.6 (pi-0.6) used for?
π0.6 (pi-0.6) works in Robotics, Vision, and is recorded as handling robotic manipulation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run π0.6 (pi-0.6)?
None. π0.6 (pi-0.6) 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 π0.6 (pi-0.6) open source?
No. π0.6 (pi-0.6) has not had its weights published, so it exists only as a service controlled by its owner.
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.