Dunfey · Hotel WWDC as data, est. 1983
Front desk everything
Years
Topics

WWDC26 · 14 min · AI & Machine Learning

Run local agentic AI on the Mac using MLX

Run AI agents locally with privacy, low latency, and offline access. Dive into how MLX advancements and Mac hardware make powerful agentic workflows possible entirely on-device. You’ll explore code agents such as OpenCode, see how they integrate into Xcode, learn techniques for multi-Mac scaling, and discover how to integrate tools seamlessly — without ever leaving your machine.

Watch at developer.apple.com ↗

Transcript all transcripts

Chapters

Code shown on screen · 3 snippets

Set up MLX-LM and start the local server bash · at 4:40 ↗ 
# 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!"}]}'
Configure an agent to use your local MLX server json · at 5:18 ↗ 
{
  "$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"
        }
      }
    }
  }
}
Launch distributed inference with MLX bash · at 8:33 ↗ 
mlx.launch --hostfile hosts.json \
  --backend jaccl \
  /remote/path/to/mlx_lm.server \
  --model mlx-community/Qwen-3.5-122B-A3B-8bit

Resources