sickn33/agentic-awesome-skills/mac-mini-llm-lab

# Update macOS
softwareupdate --install --all
 
# Install Xcode command-line tools
xcode-select --install
 
# Install Homebrew
# Obtain the official Homebrew installer at a reviewed version, inspect it,
# and run the verified local file only after installation authorization.
 
# 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

# 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

# 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

<!-- ~/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>127.0.0.1:11434</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

# Prevent idle sleep on this desktop (record existing values for rollback)
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 U 03:55:00 poweron U 04:00:00
 
# Check power settings
pmset -g

# 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

# 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

brew install caddy
 
# Caddyfile
cat > /opt/homebrew/etc/Caddyfile << 'EOF'
llm.local:443 {
    tls internal
    reverse_proxy localhost:11434
 
    @api path /v1/*
    handle @api {
        reverse_proxy localhost:11434
    }
}
 
webui.local:443 {
    tls internal
    reverse_proxy localhost:3000
}
EOF
 
brew services start caddy

# Run Open WebUI via Docker
docker run -d \
  --name open-webui \
  -p 3000:8080 \
  -e OLLAMA_BASE_URL=http://host.docker.internal:11434 \
  -e WEBUI_AUTH=true \
  -v open-webui:/app/backend/data \
  --restart unless-stopped \
  ghcr.io/open-webui/open-webui:main
 
# Or install Docker first if not available
brew install --cask docker

# Health check script
cat > ~/scripts/llm-health.sh << 'SCRIPT'
#!/bin/bash
# Check Ollama
if curl -sf http://localhost:11434/api/tags > /dev/null; then
    echo "$(date): Ollama OK"
    curl -s http://localhost:11434/api/ps | python3 -m json.tool
else
    echo "$(date): Ollama DOWN"
    # Restart
    launchctl kickstart -k gui/$(id -u)/com.ollama.serve
fi
 
# System stats
echo "CPU: $(top -l 1 -n 0 | grep 'CPU usage')"
echo "Memory: $(vm_stat | head -5)"
echo "Disk: $(df -h / | tail -1)"
echo "Thermal: $(sudo powermetrics --samplers smc -n 1 2>/dev/null | grep 'CPU die' || echo 'N/A')"
SCRIPT
chmod +x ~/scripts/llm-health.sh
 
# Schedule health check every 5 minutes
# Add to crontab: crontab -e
# */5 * * * * ~/scripts/llm-health.sh >> ~/logs/llm-health.log 2>&1

# Enable FileVault disk encryption
sudo fdesetup enable
 
# Enable firewall
sudo /usr/libexec/ApplicationFirewall/socketfilterfw --setglobalstate on
sudo /usr/libexec/ApplicationFirewall/socketfilterfw --setstealthmode on
 
# Disable unnecessary sharing services
sudo launchctl disable system/com.apple.screensharing
sudo launchctl disable system/com.apple.AirPlayXPCHelper
 
# Set strong admin password
# System Settings > Users & Groups
 
# Restrict Ollama to local network only (if not using Tailscale)
# Set OLLAMA_HOST=127.0.0.1 in launchd plist

# Increase file descriptor limits for concurrent requests
sudo launchctl limit maxfiles 65536 200000
 
# Check unified memory pressure
memory_pressure
 
# Monitor GPU usage (Metal)
sudo powermetrics --samplers gpu_power -n 1
 
# Optimize for inference (disable Spotlight indexing on model dirs)
mdutil -i off ~/.ollama