A practical Mac mini setup for a personal AI backend
The setup uses a MacBook Pro M4 Pro with 48GB of memory and a Mac mini M4 with 16GB of memory to build a personal AI assistant and knowledge system. The goal is not just to run a local LLM, but to create a persistent “second brain” that remembers work, health, projects, documents, and personal knowledge over time. The MacBook would run Hermes, a local Qwen model, browser and computer automation, voice and chat controls, and the main decision-making layer.
The Mac mini would stay on as the backend for , document indexing, a , embedding generation, background summaries, MCP tool servers, and nightly maintenance such as re-indexing, , summaries, and backups. The would include PDFs, emails, notes, drawings, and similar personal material. The proposed knowledge structure follows Andrej Karpathy’s LLM-WIKI idea inside an , with fixed source documents, AI-maintained Markdown pages, an index page, and Obsidian wiki links connecting everything.
The would retrieve relevant information, while the Obsidian wiki would become the readable and maintained . The two Macs would be linked with a CalDigit TS3 Plus dock, an OWC cable, and Thunderbolt Networking.
Key points
- The MacBook Pro is planned as the front-end machine for reasoning, automation, voice, chat, and decisions.
- The Mac mini is planned as the always-on backend for memory, indexing, summaries, backups, and maintenance.
- The would use Obsidian with raw source documents and AI-maintained Markdown pages.
- A and embedding generation would help retrieve relevant information from personal documents.
- Thunderbolt Networking would connect the two Macs directly for fast communication.