Octo-Small

Robotics Open (Restricted)
27M
Parameters

About Octo-Small

Octo-Small is an AI model developed by University of California (UC) Berkeley, in the robotics category, released in 2024, made available as an open-weights model with 0B params.

On this page you'll find Octo-Small's full specifications. Review provider pricing and benchmark scores below, or compare Octo-Small head-to-head with other robotics models.

Links

Community

Would you run Octo-Small again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Octo-Small

Frequently asked questions

What is Octo-Small?

Octo-Small is an AI model developed by University of California (UC) Berkeley, in the robotics category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Octo-Small?

Octo-Small was developed by University of California (UC) Berkeley and released in 2024.

Is Octo-Small open source or proprietary?

Octo-Small ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Octo-Small cost?

Pricing for Octo-Small depends on the provider. See the providers table on this page for the latest API rates.

How does Octo-Small perform on benchmarks?

Benchmark scores for Octo-Small are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about Octo-Small?