tiny-llm
GitHubA course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
Claude Desktop Configuration
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"tiny-llm": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-tiny-llm"
]
}
}
}