Mac mini M4 + AnythingLLM: chat with your files, nothing leaves the Mac
A beginner-friendly walkthrough: Ollama runs Llama 3 on an M4 Mac mini, AnythingLLM Desktop provides the UI and local LanceDB vector store.
Solo2-10 peopleDocument search / chat with filesWriting assistantUnder $1kSensitivity: High (client/confidential)
Hardware
| Item | Approx. price (as of 2026-10-16) |
|---|---|
| Apple Mac mini (M4, 16GB RAM minimum recommended) | Not stated in source |
| Apple Mac mini M4 (16GB, 256GB) (Best Buy, related current price) | $599.00 |
Source prices are as stated by the source. Retailer offers: prices checked 2026-10-16, may change. Some links may be affiliate links; we may earn a commission at no extra cost to you. This never changes what we list.
Software stack
- Ollama
- AnythingLLM Desktop
- LanceDB (built in)
Models used
- Llama 3 (ollama run llama3, ~4.7GB)
Good at
- All processing local on the M4
- Very simple GUI setup
- Optional hybrid mode with cloud keys
Weak at
- 16GB limits model size
Rough total cost
Not stated in source.
Getting started
- Download Ollama for macOS from ollama.com and install command line tools.
- In Terminal: ollama run llama3
- Download AnythingLLM Desktop and run the setup wizard.
- Choose Ollama as LLM, select llama3, keep default LanceDB.
- Create a workspace and upload documents.
Source & credit
Mac Mini AI (Local LLMs) — Benjamin S Powell
Summarized from the source; quotes are the source author's words. Check the original before buying.