Humanoid Locomotion

Closed weights University of California (UC) Berkeley 8M parameters February 2024

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
University of California (UC) Berkeley
Organisation type
Academia
Country
United States of America
Published
29 February 2024
Authors
Ilija Radosavovic, Bike Zhang, Baifeng Shi, Jathushan Rajasegaran, Sarthak Kamat, Trevor Darrell, Koushil Sreenath, Jitendra Malik

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
8M

Largest model trained has 8M params. Note actual model used in real-world experiments appears to be 2M, to improve latency. See sections 5.1 and 5.9.

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
Likely
Citations
108

Sources

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

Reference
Humanoid Locomotion as Next Token Prediction
Last updated
25 May 2026

What the numbers mean

Where it came from

Humanoid Locomotion was published by University of California (UC) Berkeley, in United States of America, in February 2024. It comes out of academia.

It works in Robotics, and is recorded as doing animal (human/non-human) imitation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Answers

Humanoid Locomotion — common questions

01

Is Humanoid Locomotion open source?

No. Humanoid Locomotion has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does Humanoid Locomotion have?

Humanoid Locomotion has 8M parameters. Largest model trained has 8M params. Note actual model used in real-world experiments appears to be 2M, to improve latency. See sections 5.1 and 5.9. 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.

03

Who created Humanoid Locomotion?

Humanoid Locomotion was published by University of California (UC) Berkeley, based in United States of America, categorised as academia.

04

When was Humanoid Locomotion released?

Humanoid Locomotion was published in February 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Humanoid Locomotion used for?

Humanoid Locomotion works in Robotics, and is recorded as handling animal (human/non-human) imitation. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run Humanoid Locomotion?

None. Humanoid Locomotion 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.

Source

Original publication

Record last updated 25 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.