Mac Mini M5作为本地AI服务器 2026：全天候LLM、Whisper、RAG与语音助手

# Install Homebrew (if not already installed)
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

# Install Ollama
brew install ollama

# Start as background service (auto-starts on reboot)
brew services start ollama

# Verify it's running
curl http://localhost:11434/api/version

# Allow Ollama to listen on all interfaces (not just localhost)
echo 'export OLLAMA_HOST=0.0.0.0:11434' >> ~/.zshrc
echo 'export OLLAMA_MAX_LOADED_MODELS=3' >> ~/.zshrc
echo 'export OLLAMA_KEEP_ALIVE=1h' >> ~/.zshrc
source ~/.zshrc

# Restart Ollama with new settings
brew services restart ollama

# Verify listening on all interfaces
lsof -i :11434

# General-purpose LLM
ollama pull llama3.1:8b

# Alternative: faster, similar quality
ollama pull mistral:7b

# For coding tasks
ollama pull deepseek-coder-v2:16b

# Embedding model for RAG
ollama pull nomic-embed-text

# Find current local IP
ipconfig getifaddr en0

# Or use Bonjour - access at hostname.local
scutil --get LocalHostName
# 示例：macmini → 通过 http://macmini.local:11434 访问

sudo pmset -a sleep 0
sudo pmset -a displaysleep 1
sudo pmset -a powernap 0
sudo pmset -a hibernatemode 0

# Verify settings
pmset -g

# 从同一网络的笔记本/手机/平板：
curl http://macmini.local:11434/api/chat -d '{
  "model": "llama3.1:8b",
  "messages": [{"role": "user", "content": "来自手机的问候！"}]
}'

# 方案1：Tailscale（推荐）— 安装在Mac Mini上
brew install --cask tailscale
# 通过Tailscale应用登录 — Mac Mini获得私有IP
# 从任何安装了Tailscale的地方访问：
curl http://macmini.tailnet.ts.net:11434/api/chat -d '{...}'

# 方案2：Cloudflare Tunnel（Web访问）
brew install cloudflared
cloudflared tunnel create ai-server
cloudflared tunnel route dns ai-server ai.yourdomain.com
# 从任何地方通过 https://ai.yourdomain.com 访问

# 通过Docker安装ChromaDB
brew install --cask docker
docker run -d -p 8000:8000 -v ~/chromadb:/data chromadb/chroma

# 索引文档（Python）
from langchain_community.embeddings import OllamaEmbeddings
from langchain_community.vectorstores import Chroma

embeddings = OllamaEmbeddings(
    model="nomic-embed-text",
    base_url="http://localhost:11434"
)
vectordb = Chroma.from_documents(
    documents=splits,
    embedding=embeddings,
    persist_directory="./chroma_db"
)

// ~/.continue/config.json
{
  "models": [{
    "title": "Mac Mini DeepSeek Coder",
    "provider": "ollama",
    "model": "deepseek-coder-v2:16b",
    "apiBase": "http://macmini.local:11434"
  }]
}

#!/bin/bash
echo "=== AI Server Health Check ==="
echo "Date: $(date)"

if pgrep -x "ollama" > /dev/null; then
    echo "✓ Ollama running"
else
    echo "✗ Ollama NOT running - restarting"
    brew services restart ollama
fi

if curl -s http://localhost:11434/api/version > /dev/null; then
    echo "✓ API responding"
else
    echo "✗ API NOT responding"
fi

df -h / | tail -1
uptime