Laboratório LLM no Mac mini

Transforme um Mac mini em um aparelho de IA local, sempre ativo e com baixo ruído.

Quando Usar Esta Habilidade

Use esta habilidade quando:

• Configurar um servidor dedicado de inferência LLM local
• Construir um ambiente de desenvolvimento de IA privado
• Precisar de serviço de modelos sempre ativo sem custos de nuvem
• Executar modelos que exigem memória unificada do Apple Silicon (32-192GB)
• Criar um servidor de IA para um laboratório doméstico para uma pequena equipe

Pré-requisitos

• Mac mini com Apple Silicon (M2/M3/M4, 16GB+ de memória unificada recomendado)
• macOS Sonoma 14+ ou Sequoia 15+
• Conexão Ethernet (recomendado em vez de Wi-Fi)
• UPS para proteção de energia (opcional, mas recomendado)

Configuração Inicial do Sistema

# Update macOS
softwareupdate --install --all

# Install Xcode command-line tools
xcode-select --install

# Install Homebrew
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

# Core packages
brew install tmux htop btop wget jq git neovim

# Python environment (for MLX and custom scripts)
brew install python@3.12 uv

# Monitoring
brew install prometheus node_exporter

Configuração do Ollama

# Install Ollama
brew install ollama

# Pull models based on your RAM
# 16GB Mac mini:
ollama pull llama3.1:8b
ollama pull nomic-embed-text
ollama pull codellama:7b

# 32GB Mac mini:
ollama pull llama3.1:8b
ollama pull qwen2.5:14b
ollama pull deepseek-coder-v2:16b
ollama pull nomic-embed-text

# 64GB+ Mac mini:
ollama pull llama3.1:70b
ollama pull qwen2.5:32b
ollama pull codellama:34b

# Verify Metal acceleration
ollama run llama3.1:8b --verbose
# Look for: "metal" in output

Framework MLX (Nativo do Apple Silicon)

O MLX executa modelos nativamente no Apple Silicon com excelente desempenho:

# Install MLX
uv pip install mlx mlx-lm

# Run a model
python3 -c "
from mlx_lm import load, generate
model, tokenizer = load('mlx-community/Llama-3.1-8B-Instruct-4bit')
response = generate(model, tokenizer, prompt='Explain Docker in 3 sentences', max_tokens=200)
print(response)
"

# MLX server (OpenAI-compatible API)
uv pip install mlx-lm[server]
mlx_lm.server --model mlx-community/Llama-3.1-8B-Instruct-4bit --port 8080

Início Automático com launchd

<!-- ~/Library/LaunchAgents/com.ollama.serve.plist -->
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
    <key>Label</key>
    <string>com.ollama.serve</string>
    <key>ProgramArguments</key>
    <array>
        <string>/opt/homebrew/bin/ollama</string>
        <string>serve</string>
    </array>
    <key>EnvironmentVariables</key>
    <dict>
        <key>OLLAMA_HOST</key>
        <string>0.0.0.0</string>
        <key>OLLAMA_NUM_PARALLEL</key>
        <string>4</string>
        <key>OLLAMA_MAX_LOADED_MODELS</key>
        <string>2</string>
        <key>OLLAMA_FLASH_ATTENTION</key>
        <string>1</string>
    </dict>
    <key>RunAtLoad</key>
    <true/>
    <key>KeepAlive</key>
    <true/>
    <key>StandardOutPath</key>
    <string>/tmp/ollama.log</string>
    <key>StandardErrorPath</key>
    <string>/tmp/ollama.err</string>
</dict>
</plist>

# Load the service
launchctl load ~/Library/LaunchAgents/com.ollama.serve.plist

# Check status
launchctl list | grep ollama

# Unload if needed
launchctl unload ~/Library/LaunchAgents/com.ollama.serve.plist

Energia e Confiabilidade

# Prevent sleep (keeps running with lid closed on Mac mini)
sudo pmset -a disablesleep 1
sudo pmset -a sleep 0

# Auto-restart after power failure
sudo pmset -a autorestart 1

# Schedule weekly reboot (Sunday 4 AM)
sudo pmset repeat shutdown MTWRFSU 03:55:00
sudo pmset repeat poweron MTWRFSU 04:00:00

# Check power settings
pmset -g

Acesso Remoto

Tailscale (Recomendado)

# Install Tailscale for easy secure remote access
brew install --cask tailscale

# Enable from menu bar, authenticate
# Access your Mac mini from anywhere: http://mac-mini:11434

Fortalecimento do SSH

# Enable remote login
sudo systemsetup -setremotelogin on

# Edit SSH config
sudo nano /etc/ssh/sshd_config
# Add:
# PasswordAuthentication no
# PubkeyAuthentication yes
# PermitRootLogin no
# AllowUsers yourusername

# Restart SSH
sudo launchctl unload /System/Library/LaunchDaemons/ssh.plist
sudo launchctl load /System/Library/LaunchDaemons/ssh.plist

Proxy Reverso com Caddy

brew install caddy

# Caddyfile
cat > /opt/homebrew/etc/Caddyfile << 'EOF'

…