apple/coreai-models

Health v2 · maintenance only

Flags: prerelease_only young

Adoption not part of the score

1999 stars · 183 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Apple's repository of model export recipes, Python primitives, and Swift runtime utilities for building on-device AI with the Core AI framework. It converts popular open-source models (e.g., from Hugging Face) into standalone .aimodel files that run on macOS and iOS via Apple silicon.

Use cases

• export huggingface models to run on-device on iphone
• convert pytorch models to core ai format
• run llms locally on a mac
• integrate on-device ai models into an ios app
• author custom models for apple core ai in pytorch
• find supported models for core ai export
• help coding agents use core ai effectively

When to choose

• you want to deploy open-source models on-device on macOS or iOS with Apple's Core AI framework
• you need export recipes for popular Hugging Face models to .aimodel format
• you're building an Apple-silicon app that runs language or diffusion models locally
• you want Swift runtime utilities for model integration in Xcode projects

When to avoid

• you target Android, Windows, or Linux deployment
• you need server-side or cloud GPU inference
• you can't upgrade to macOS/iOS 27 and Xcode 27
• you need a framework-agnostic inference solution independent of Apple's ecosystem

Facets

library · maturity active

machine-learning llm-inference sdk cli developer-tools machine-learning artificial-intelligence large-language-models apple-ecosystem developer-tools python cli on-device-ai core-ai model-export apple-silicon pytorch aimodel swift-package agent-skills macos ios swift

Member repositories

For agents

markdown · JSON · MCP: product_card(name="apple/coreai-models")