Robot Parkour
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
- Shanghai Qi Zhi institute,Stanford University,Carnegie Mellon University (CMU),Tsinghua University
- Organisation type
- Academia,Academia,Academia
- Country
- China, United States of America
- Published
- 12 September 2023
- Authors
- Ziwen Zhuang, Zipeng Fu, Jianren Wang, Christopher Atkeson, Soeren Schwertfeger, Chelsea Finn, Hang Zhao
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Robotics
- Task
- Animal (human/non-human) imitation
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
- 500K
- Training data
- tokens
Parkour policy details on page 8, table 11.
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA GeForce RTX 3090
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
- Open source
MIT license for training and inference code: https://github.com/ZiwenZhuang/parkour
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
- SOTA improvement
- Record confidence
- Confident
- Citations
- 274
I do not see any standard benchmarks that they are claiming SOTA on
Sources
Where this record came from and when it was last checked.
- Reference
- Robot Parkour Learning
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
Robot Parkour was published by Shanghai Qi Zhi institute,Stanford University,Carnegie Mellon University (CMU),Tsinghua University, in the country recorded as China, during September 2023. The category the publisher falls under is academia,Academia,Academia.
It works in the domain of Robotics, and is recorded as performing the task of animal (human/non-human) imitation.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
The reason it appears in this catalogue at all: sOTA improvement.
Answers
Robot Parkour — common questions
Robot Parkour— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Robot Parkour— how many parameters does it have?
It has a parameter count of 500K. Parkour policy details on page 8, table 11. 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.
Robot Parkour— who created it?
It was published by Shanghai Qi Zhi institute,Stanford University,Carnegie Mellon University (CMU),Tsinghua University, based in China, an organisation categorised as academia,Academia,Academia.
Robot Parkour— when was it released?
It was published in September 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.
Robot Parkour— what is it used for?
It works in the domain of Robotics, and is recorded as handling the task of animal (human/non-human) imitation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Robot Parkour— what GPU do I need to run it?
None. This 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.