LmCast :: Stay tuned in

Laya (OS Jev) on Mac M4 CoreML Offline (45 decisions per second)

Recorded: Sept. 20, 2026, 5 p.m.

Original Summarized

Laya on Mac m4 CoreML Offline · GitHub

Skip to content

Search Gists

Search Gists

All gists
Back to GitHub

Sign in

Sign up

Sign in

Sign up

You signed in with another tab or window. Reload to refresh your session.
You signed out in another tab or window. Reload to refresh your session.
You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

Instantly share code, notes, and snippets.

fordnox/laya.sh

Last active
September 20, 2026 16:45

Show Gist options

Download ZIP


Star

1
(1)

You must be signed in to star a gist

Fork

0
(0)

You must be signed in to fork a gist


Embed

Select an option

Embed
Embed this gist in your website.

Share
Copy sharable link for this gist.

Clone via HTTPS
Clone using the web URL.

No results found


Learn more about clone URLs


Clone this repository at <script src="https://gist.github.com/fordnox/e592d0f68b543fd044be8e6d040863a0.js"></script>

Save fordnox/e592d0f68b543fd044be8e6d040863a0 to your computer and use it in GitHub Desktop.

Code

Revisions
2

Stars
1


Embed

Select an option

Embed
Embed this gist in your website.

Share
Copy sharable link for this gist.

Clone via HTTPS
Clone using the web URL.

No results found


Learn more about clone URLs


Clone this repository at <script src="https://gist.github.com/fordnox/e592d0f68b543fd044be8e6d040863a0.js"></script>

Save fordnox/e592d0f68b543fd044be8e6d040863a0 to your computer and use it in GitHub Desktop.

Download ZIP

Laya on Mac m4 CoreML Offline


Raw

laya.sh

mkdir test-laya

cd test-laya

uv init

uv add 'laya-coreml[demo]'

hf download aac6fef/laya-multilingual-coreml-ane --local-dir models/snake

uv run laya-coreml-snake --model models/snake

fordnox

commented

Sep 20, 2026

•

edited

Loading

Uh oh!

There was an error while loading. Please reload this page.




Copy link



Copy Markdown


Author

testing https://github.com/mizorewww/laya-coreml

LAYA-CORE-ML.mov

Sorry, something went wrong.

Uh oh!

There was an error while loading. Please reload this page.


Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms

Privacy

Security

Status

Community

Docs

Contact

Manage cookies

Do not share my personal information

You can’t perform that action at this time.

The provided material outlines a process for executing Laya with CoreML functionality offline on a Mac with an M4 chip, presented via a series of command-line instructions from a GitHub Gist. The workflow is designed to set up and run Laya models, specifically demonstrating an offline capability. The initial steps involve setting up a local testing environment by creating a directory named test-laya and navigating into it. Subsequently, the process utilizes the uv package manager to initialize a project and install necessary dependencies, specifically adding the 'laya-coreml[demo]' package.

The core of the procedure involves downloading a specific Laya multilingual CoreML model from the Hugging Face repository, which is sourced with the identifier aac6fef/laya-multilingual-coreml-ane, and saving it to a local directory structure. This downloaded model is placed within a models/snake subdirectory. Finally, the execution step runs the Laya application utilizing the installed CoreML components and referencing the previously downloaded model, specifically invoking laya-coreml-snake with the model path defined. This sequence demonstrates the practical steps required to initialize a software environment, acquire necessary machine learning assets offline, and execute a complex model inference process using CoreML on Apple silicon hardware. The reference also points to related testing code, suggesting an emphasis on reproducible and verifiable implementation within the framework.