Course · 4 chapters

On-Device & Edge AI

Run AI directly on a phone or Mac with no cloud round-trip. Build with Apple Foundation Models, Gemini Nano, and MLX across 4 advanced chapters for app engineers.

Paidadvanced4 chapters78 minEnglish + 6 languagesCertificate on completion

What you'll be able to do

  • Embed Apple Foundation Models in iOS apps
  • Ship on-device AI to Android with Gemini Nano
  • Run local models on Apple Silicon with MLX
  • Choose on-device or cloud inference
  • Match edge platforms to your use case

What's inside

  1. 1
    On-Device & Edge AI: Start Here

    A 12-minute orientation to the On-Device & Edge AI skill path — the three platforms where your model can run without a cloud round-trip, and how to pick yours

    12 min
  2. 2
    Apple Foundation Models for Swift Developers

    Ship a capable ~3B LLM inside your iOS app — guided generation, tool calling, and when to still reach for Claude

    22 min
  3. 3
    Gemini Nano and AICore on Android

    Ship on-device AI to 140M+ Android devices — AICore as a shared system service, ML Kit GenAI APIs, and Gemma 4 agentic intelligence

    22 min
  4. 4
    MLX in Practice: Local Inference on Apple Silicon

    Run arbitrary open models on your Mac — unified memory, JANG quantization, Ollama + MLX, and the honest limits of a single-user inference node

    22 min

Frequently asked questions

What will I learn in this on-device AI course?
You learn to run AI models directly on a device with no cloud call, using Apple Foundation Models in iOS apps, Gemini Nano and AICore on Android, and MLX for local inference on Apple Silicon. The path also covers quantization, tool calling, and when to fall back to a cloud model like Claude.
Who is this course for?
It is built for software and AI engineers, especially iOS, Android, and Mac developers who want to add private, low-latency AI features that work without a server. The level is advanced and assumes you already ship production app code.
Do I need coding experience to take this course?
Yes. This is an advanced engineering path that works with Swift on iOS, Android system APIs, and Python tooling such as MLX and Ollama, so you should already be comfortable building and running app code.
How long is the course and is there a certificate?
The path has 4 chapters totaling about 78 minutes, with a 12-minute orientation and three 22-minute platform chapters on Apple, Android, and Mac. You earn a certificate of completion after finishing every chapter.
Is this course free?
No, On-Device & Edge AI is a paid path included in the AI Academy subscription. It sits in the AI for Engineers track alongside the other AI engineering paths.

Earn a certificate

Complete all chapters to receive your certificate of completion.