Local AI on a Mac Studio with Ollama

Reviewed by the Contractor AI Shop research team · Last updated Oct 14, 2026 · How we research

Why: keep bids, specs and pricing private, with no per-token fees. Apple silicon unified memory lets a Mac Studio hold large models.

1. Hardware

Choose RAM by model size: 64GB is comfortable for about 30B-class models and 128GB+ for 70B-class models. See Apple Mac Studio.

2. Install Ollama

Download from ollama.com/download/mac (docs: Ollama on macOS). Then run:

ollama pull llama3.1:8b
ollama run llama3.1:8b

3. Add a chat UI

Install Open WebUI and point it at Ollama (http://localhost:11434), then upload specs/RFIs for Q&A.

4. Automate

Call the Ollama API from scripts or n8n AI workflows.

5. Optional: MLX

mlx-lm runs MLX-format models natively. LM Studio is a GUI alternative.