My local model setup on an M4 Pro Mac Mini
- ID
- 20763
- Status
- summarized
- Published
- 02 Sep 2026, 6:30 AM
- Fetched
- 04 Sep 2026, 6:14 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://lws.io/blog/my-local-model-setup/
- Source URL
- https://hnrss.org/best
Summary
- Score
- 8.0
- Created
- 04 Sep 2026, 6:16 AM
- Tags
- Audience
- developersvibe_codersai_agent_usersai/ml_learners
What happened
Kevin Lewis details his local LLM setup on an M4 Pro Mac mini with 48GB RAM, which handles his Hermes agent backend and daily chat queries in about 30 minutes of setup. The stack uses Qwen3.6-35B and Gemma-4-E4B models via oMLX, connected across devices using Tailscale. He cites cost predictability, data privacy, and AI sovereignty as primary reasons for moving away from cloud APIs that were costing him $400/month.
Why it matters
If you are spending hundreds a month on cloud LLM APIs and worrying about data privacy or sudden model degradations, this detailed hardware and software stack shows exactly how to host your own agent backend and chat clients locally for a flat hardware cost.
Discussion angle
Comparing the trade-offs of a local Mac mini setup versus ongoing $400/month API subscriptions for running AI agents and coding assistants.