View in English

  • Apple Developer
    • Get Started

    Explore Get Started

    • Overview
    • Learn
    • Apple Developer Program

    Stay Updated

    • Latest News
    • Hello Developer
    • Platforms

    Explore Platforms

    • Apple Platforms
    • iOS
    • iPadOS
    • macOS
    • tvOS
    • visionOS
    • watchOS
    • App Store

    Featured

    • Design
    • Distribution
    • Games
    • Accessories
    • Web
    • Home
    • CarPlay
    • Technologies

    Explore Technologies

    • Overview
    • Xcode
    • Swift
    • SwiftUI

    Featured

    • Accessibility
    • App Intents
    • Apple Intelligence
    • Games
    • Machine Learning & AI
    • Security
    • Xcode Cloud
    • Community

    Explore Community

    • Overview
    • Meet with Apple events
    • Community-driven events
    • Developer Forums
    • Open Source

    Featured

    • WWDC
    • Swift Student Challenge
    • Developer Stories
    • App Store Awards
    • Apple Design Awards
    • Apple Developer Centers
    • Documentation

    Explore Documentation

    • Documentation Library
    • Technology Overviews
    • Sample Code
    • Human Interface Guidelines
    • Videos

    Release Notes

    • Featured Updates
    • iOS
    • iPadOS
    • macOS
    • watchOS
    • visionOS
    • tvOS
    • Xcode
    • Downloads

    Explore Downloads

    • All Downloads
    • Operating Systems
    • Applications
    • Design Resources

    Featured

    • Xcode
    • TestFlight
    • Fonts
    • SF Symbols
    • Icon Composer
    • Support

    Explore Support

    • Overview
    • Help Guides
    • Developer Forums
    • Feedback Assistant
    • Contact Us

    Featured

    • Account Help
    • App Review Guidelines
    • App Store Connect Help
    • Upcoming Requirements
    • Agreements and Guidelines
    • System Status
  • Quick Links

    • Events
    • News
    • Forums
    • Sample Code
    • Videos
 

Vídeos

Abrir menu Fechar menu
  • Coleções
  • Todos os vídeos
  • Sobre

Mais vídeos

  • Sobre
  • Resumo
  • Código
  • Execute IA agêntica localmente no Mac usando o MLX

    Execute agentes de IA localmente com privacidade, baixa latência e acesso offline. Descubra como os avanços do MLX e o hardware do Mac viabilizam poderosos fluxos de trabalho agênticos inteiramente no dispositivo. Você explorará agentes de código, como OpenCode, verá como eles se integram ao Xcode, aprenderá técnicas para ampliar a capacidade usando vários Macs e descobrirá como integrar ferramentas perfeitamente, sem sair da sua máquina.

    Capítulos

    • 0:00 - Introduction
    • 0:32 - The chat and agentic loop
    • 2:42 - Local agentic AI stack
    • 4:36 - Setting up your own agent
    • 5:39 - Making agents fast
    • 6:53 - Concurrency and distributed inference
    • 9:20 - More examples
    • 13:01 - Next steps

    Recursos

    • MLX Swift LM on GitHub
    • MLX Swift Examples
    • MLX Examples
    • MLX Swift
    • MLX LM - Python API
    • MLX Explore - Python API
    • MLX Framework
    • MLX
      • Vídeo HD
      • Vídeo SD

    Vídeos relacionados

    WWDC26

    • Explore a computação numérica em Swift com o MLX
    • Explore inferência e treinamento distribuído com o MLX

    WWDC25

    • Explore os LLMs (grandes modelos de linguagem) no Apple Silicon com o MLX
    • Introdução ao MLX para Apple Silicon
  • Buscar neste vídeo...
    • 4:40 - Set up MLX-LM and start the local server

      # Step 1: Install MLX-LM
      pip install mlx-lm
      
      # Step 2: Start the server
      mlx_lm.server --model mlx-community/Qwen-3.5-4B-8bit
      
      # Step 3: Point your agent to the server
      curl -X POST \
        http://127.0.0.1:8080/v1/chat/completions \
        -H "Content-Type: application/json" \
        -d '{"model":"default_model","messages":[{"role":"user","content":"Hello!"}]}'
    • 5:18 - Configure an agent to use your local MLX server

      {
        "$schema": "https://opencode.ai/config.json",
        "model": "mlx/default_model",
        "small_model": "mlx/default_model",
        "provider": {
          "mlx": {
            "npm": "@ai-sdk/openai-compatible",
            "name": "MLX (local)",
            "options": {
              "baseURL": "http://127.0.0.1:8080/v1"
            },
            "models": {
              "default_model": {
                "name": "Default MLX Model"
              }
            }
          }
        }
      }
    • 8:33 - Launch distributed inference with MLX

      mlx.launch --hostfile hosts.json \
        --backend jaccl \
        /remote/path/to/mlx_lm.server \
        --model mlx-community/Qwen-3.5-122B-A3B-8bit
    • 0:00 - Introduction
    • Overview of building and running agentic AI workflows entirely on Mac using MLX — no cloud, no API keys, just your hardware.

    • 0:32 - The chat and agentic loop
    • How traditional chat differs from the agentic loop: the model decides what to do, calls tools to run commands, read files, and hit APIs, observes the results, and iterates — all running locally for privacy and offline availability.

    • 2:42 - Local agentic AI stack
    • A walkthrough of the four-layer stack powering local agentic AI on the Mac: MLX (array framework for Apple Silicon), MLX-LM (model loading, quantization, and fine-tuning), MLX-LM Server (OpenAI-compatible HTTP server), and the agent layer — including popular tools like Ollama, LM Studio, and vLLM.

    • 4:36 - Setting up your own agent
    • Three steps to go from zero to a fully local agentic workflow: install MLX-LM with pip, start the server with a tool-calling model, and configure your agent to point at the local endpoint.

    • 5:39 - Making agents fast
    • How MLX tackles the first challenge of agentic workloads — efficiently processing large contexts with hundreds of thousands of tokens — including how M5 Neural Accelerators accelerate prompt processing speed.

    • 6:53 - Concurrency and distributed inference
    • How MLX handles continuous batching for concurrent multi-agent requests, and distributed inference to spread large models across multiple Macs over Thunderbolt.

    • 9:20 - More examples
    • Two-part live demo building SwiftUI apps entirely on-device. First, using OpenCode with MLX to generate a complete SwiftUI project from a description; then, using Xcode's agentic coding capabilities to build and fix a SwiftUI app — all running locally.

    • 13:01 - Next steps
    • Summary of the full local AI stack and practical steps to get started: install MLX-LM, launch the server, and connect your agent. All shown tools are open-source and available now.

Developer Footer

  • Vídeos
  • WWDC26
  • Execute IA agêntica localmente no Mac usando o MLX
  • Open Menu Close Menu
    • iOS
    • iPadOS
    • macOS
    • tvOS
    • visionOS
    • watchOS
    • App Store
    Open Menu Close Menu
    • Swift
    • SwiftUI
    • Swift Playground
    • TestFlight
    • Xcode
    • Xcode Cloud
    • Icon Composer
    • SF Symbols
    Open Menu Close Menu
    • Accessibility
    • Accessories
    • Apple Intelligence
    • Audio & Video
    • Augmented Reality
    • Business
    • Design
    • Distribution
    • Education
    • Games
    • Health & Fitness
    • In-App Purchase
    • Localization
    • Maps & Location
    • Machine Learning & AI
    • Security
    • Safari & Web
    Open Menu Close Menu
    • Documentation
    • Downloads
    • Sample Code
    • Videos
    Open Menu Close Menu
    • Help Guides & Articles
    • Contact Us
    • Forums
    • Feedback & Bug Reporting
    • System Status
    Open Menu Close Menu
    • Apple Developer
    • App Store Connect
    • Certificates, IDs, & Profiles
    • Feedback Assistant
    Open Menu Close Menu
    • Apple Developer Program
    • Apple Developer Enterprise Program
    • App Store Small Business Program
    • MFi Program
    • Mini Apps Partner Program
    • News Partner Program
    • Video Partner Program
    • Security Bounty Program
    • Security Research Device Program
    Open Menu Close Menu
    • Meet with Apple
    • Apple Developer Centers
    • App Store Awards
    • Apple Design Awards
    • Apple Developer Academies
    • WWDC
    Read the latest news.
    Get the Apple Developer app.
    Copyright © 2026 Apple Inc. All rights reserved.
    Terms of Use Privacy Policy Agreements and Guidelines