smpanaro/more-ane-transformers

Run transformers (incl. LLMs) on the Apple Neural Engine.

21
/ 100
Experimental

If you're an AI developer working on a Mac, this project lets you run large language models (LLMs) like GPT directly on your Apple Neural Engine. It takes pre-converted CoreML models as input and generates text or other transformer outputs, utilizing your Mac's specialized hardware for faster, more efficient processing. This is designed for developers who want to leverage Apple Silicon's machine learning capabilities for their applications.

No commits in the last 6 months.

Use this if you are a developer with an Apple Silicon Mac and want to efficiently run large transformer models, including LLMs, with hardware acceleration and minimal CPU usage.

Not ideal if you are not a developer, do not have an Apple Silicon Mac, or need to run models larger than approximately 2.8 billion parameters.

AI development machine learning engineering natural language processing on-device AI model deployment
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

63

Forks

2

Language

Python

License

Last pushed

Nov 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/smpanaro/more-ane-transformers"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.