
Claude Desktop + 本地微调模型:完整设置指南
在本地运行你的微调模型,通过MCP连接到Claude Desktop,在Claude界面中获得零成本领域AI助手。完整分步设置。
Claude Desktop是强大的AI助手。你的微调模型专门用于你的领域。你可以通过MCP(Model Context Protocol)连接它们,获得Claude的界面加你的模型的领域专业知识——专门推理零API成本。
前提条件
- 已安装Claude Desktop
- 来自Ertas的微调GGUF模型
- Node.js 18+
- 8GB以上RAM
步骤1:安装和配置Ollama
# macOS / Linux
curl -fsSL https://ollama.ai/install.sh | sh
导入你的微调GGUF模型:
cat > Modelfile << 'EOF'
FROM /path/to/your-model.gguf
SYSTEM """
你是[你的领域]的专业AI助手。
"""
PARAMETER temperature 0.3
PARAMETER num_ctx 4096
EOF
ollama create my-domain-model -f Modelfile
步骤2:安装MCP SDK
mkdir claude-domain-mcp
cd claude-domain-mcp
npm init -y
npm install @modelcontextprotocol/sdk
步骤3:编写MCP服务器
创建server.mjs,定义Claude可以使用的工具,连接到你的Ollama模型。
步骤4:配置Claude Desktop
编辑配置文件,添加你的MCP服务器。使用server.mjs的绝对路径。
步骤5:验证连接
在Claude Desktop中,查找工具图标,你应该看到ask_domain_model。
Ship AI that runs on your users' devices.
Ertas early bird pricing starts at $14.50/mo — locked in for life. Plans for builders and agencies.
Ship AI that runs on your users' devices.
Early bird pricing starts at $14.50/mo — locked in for life. Plans for builders and agencies.
Keep reading

Your Vibe-Coded App Hit 1,000 Users — Now What?
You shipped fast with Cursor and Bolt. Users love it. But your OpenAI bill just crossed $200/month and it's climbing. Here's the cost survival guide for vibe-coded apps hitting real scale.

From Prototype to Product: Replacing API Calls with Fine-Tuned Models
Your Lovable/Bolt prototype works. Users are signing up. But every API call eats your margin. Here's the step-by-step playbook for migrating from cloud APIs to fine-tuned local models in production.

The Vibecoder's Guide to AI Unit Economics: When Free Tiers Stop Being Free
OpenAI's free tier got you started. But at scale, you're spending $5K/month on Opus for tasks Haiku could handle. Here's how to think about AI costs like a founder, not a hobbyist.