# apple-on-device-ai

Choose an Apple-local AI framework for iPhone, iPad, and Mac projects. The skill covers system models, custom Core ML models, and open LLMs on Apple Silicon.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 4000 installs · ★ 1237
- Author: dpearson2699
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/dpearson2699/swift-ios-skills/tree/HEAD/skills/apple-on-device-ai/SKILL.md
- Updated: 2026-07-31
- HTML: https://affpapa.org/en/nevibecode/skills/apple-on-device-ai

## What it does

The skill compares Foundation Models, Core ML, MLX Swift, and llama.cpp, matching each to common workloads. Use Foundation Models for short text generation and structured responses on Apple Intelligence devices, Core ML for custom trained models, MLX Swift for open LLMs on Apple Silicon, or llama.cpp for cross-platform GGUF inference. Foundation Models are a poor fit for code generation and complex math, so those tasks call for another backend.

The guide also covers model availability checks, session context, and conversion with coremltools. Foundation Models require an iOS 26+ or macOS 26+ device with Apple Intelligence enabled, and the system model assets need to be ready. For Swift code that loads and runs Core ML models, use the separate `coreml` skill.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/apple-on-device-ai/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/apple-on-device-ai/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/apple-on-device-ai/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/apple-on-device-ai/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install dpearson2699/swift-ios-skills apple-on-device-ai
```

2. **Manually: put the files in place**
- File: `.github/skills/apple-on-device-ai/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/dpearson2699/swift-ios-skills --path skills/apple-on-device-ai
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/apple-on-device-ai/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add dpearson2699/swift-ios-skills --skill apple-on-device-ai -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/dpearson2699/swift-ios-skills/tree/HEAD/skills/apple-on-device-ai/SKILL.md

## When to use it
- choose an Apple framework for local inference
- plan an Apple Intelligence chatbot
- run an open LLM on Apple Silicon
- convert a PyTorch model for Core ML
- compare on-device inference backends

## Example prompts
- Choose a framework for a short-response chatbot running on an iPhone.
- Compare MLX Swift with llama.cpp for an open LLM on Apple Silicon.
- Explain how to prepare a PyTorch model for Core ML with coremltools.

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 349800 installs

From the same set: [dpearson2699/swift-ios-skills](https://affpapa.org/en/nevibecode/by/dpearson2699/swift-ios-skills.md) — 86 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md