π0.5 (pi-0.5)
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
- 22 April 2025
- Authors
- Kevin Black, Noah Brown, James Darpinian, Karan Dhabalia, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, Manuel Y. Galliker, Dibya Ghosh, Lachy Groom, Karol Hausman, Brian Ichter, Szymon Jakubczak, Tim Jones, Liyiming Ke, Devin LeBlanc, Sergey Levine, Adrian Li-Bell, Mohith Mothukuri, Suraj Nair, Karl Pertsch, Allen Z. Ren, Lucy Xiaoyang Shi, Laura Smith, Jost Tobias Spring…
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
- PaliGemma
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
- 3.3B
- Training data
- tokens
Fig. 3: Model overview pre-training: - PaliGemma (3B): SigLIP (400M) + Gemma (2.6B) - FAST tokenizer post-training: - pretrained VLM (3B) - action expert (300M) inference: same as post-training this is in line with π0's 3.3B parameters
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
- Citations
- 337
Sources
Where this record came from and when it was last checked.
- Reference
- $π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Last updated
- 11 February 2026
What the numbers mean
Where it came from
π0.5 (pi-0.5) was published by Physical Intelligence, in United States of America, in April 2025. The organisation is categorised as industry.
It works in Robotics, Vision, and is recorded as doing robotic manipulation.
It builds on PaliGemma, which is why it shares that model's general shape and size.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
π0.5 (pi-0.5) — common questions
Is π0.5 (pi-0.5) open source?
No. π0.5 (pi-0.5) has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does π0.5 (pi-0.5) have?
π0.5 (pi-0.5) has 3.3B parameters. Fig. 3: Model overview pre-training: - PaliGemma (3B): SigLIP (400M) + Gemma (2.6B) - FAST tokenizer post-training: - pretrained VLM (3B) - action expert (300M) inference: same as post-training this is in line with π0's 3.3B 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.
Who created π0.5 (pi-0.5)?
π0.5 (pi-0.5) was published by Physical Intelligence, based in United States of America, categorised as industry.
When was π0.5 (pi-0.5) released?
π0.5 (pi-0.5) was published in April 2025.
What is π0.5 (pi-0.5) used for?
π0.5 (pi-0.5) 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 π0.5 (pi-0.5)?
None. π0.5 (pi-0.5) 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.
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.