关于 mac-mini-llm-lab
面向希望在 Mac mini 上运行本地大模型服务的用户,介绍搭建常驻 AI 主机的步骤。内容涵盖 Ollama、MLX、远程访问、自动启动、安全和监控。
主要功能
- 01安装并运行 Ollama 与 MLX
- 02配置服务自动启动和电源管理
- 03设置 Tailscale、SSH 或 Caddy 远程访问
- 04部署 Open WebUI
- 05主机安全、性能调优与监控
适用场景
- 01搭建本地大模型推理服务器
- 02创建私有 AI 开发环境
- 03为小团队提供常驻模型服务
- 04从远程网络访问 Mac mini 上的模型
安装
复制下面的命令,在终端中运行。
$
npx skills add https:/ / github.com/ bagelhole/ devops-security-agent-skills --skill mac-mini-llm-lab安装后在 Claude Code 中输入/mac-mini-llm-lab确认已加载。
详细介绍
Mac mini LLM 实验室
将 Mac mini 打造成低噪音、全天候运行的本地 AI 设备。
适用场景
在以下情况下使用此技能:
- 设置专用的本地 LLM 推理服务
- 构建私有 AI 开发环境
- 需要全天候提供模型服务,且不产生云服务费用
- 运行需要 Apple Silicon 统一内存(32-192GB)的模型
- 为小型团队搭建家庭实验室 AI 服务
前提条件
- 搭载 Apple Silicon(M2/M3/M4,推荐 16GB+ 统一内存)的 Mac mini
- macOS Sonoma 14+ 或 Sequoia 15+
- 以太网连接(推荐使用以太网而非 Wi-Fi)
- 用于电源保护的 UPS(可选,但推荐)
初始系统设置
# 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 [email protected] uv
# Monitoring
brew install prometheus node_exporter
Ollama 设置
# 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
MLX 框架(原生支持 Apple Silicon)
MLX 可在 Apple Silicon 上原生运行模型,并提供出色的性能:
# 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
使用 launchd 自动启动
<?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
电源与可靠性
# 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
远程访问
Tailscale(推荐)
# 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
SSH 安全加固
# 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
使用 Caddy 设置反向代理
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
Open WebUI 设置
# 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
监控
# 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
各模型的内存用量
| 模型 | 所需 RAM | 每秒令牌数(M2) | 每秒令牌数(M4) |
|---|---|---|---|
| llama3.1:8b (Q4) | ~5 GB | ~25 t/s | ~45 t/s |
| qwen2.5:14b (Q4) | ~9 GB | ~15 t/s | ~30 t/s |
| llama3.1:70b (Q4) | ~40 GB | ~5 t/s | ~10 t/s |
| nomic-embed-text | ~300 MB | N/A | N/A |
| codellama:13b | ~8 GB | ~18 t/s | ~35 t/s |
安全检查清单
# 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
性能调优
# 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
故障排除
| 问题 | 解决方案 |
|---|---|
| 模型加载缓慢 | 首次加载时会缓存到内存;后续加载速度很快 |
| 内存不足 | 使用较小的量化版本(Q4_K_M),降低 OLLAMA_MAX_LOADED_MODELS |
| Mac 进入睡眠 | 运行 sudo pmset -a disablesleep 1 |
| Ollama 未启动 | 检查 `launchctl list |
| Wi-Fi 网络速度慢 | 使用以太网;Wi-Fi 会增加流式响应的延迟 |
| 热降频 | 确保通风良好,并检查 powermetrics |
相关技能
- ollama-stack — 使用 Docker Compose 和 LiteLLM 的软件栈
- ssh-configuration — 安全的远程访问
- vpn-setup — 通过 WireGuard/Tailscale 远程访问
评论
支持 Markdown