Skip to content
Tech News
← Back to articles

Show HN: I made a Raspberry with Qwen my local car AI

read original more articles
Why This Matters

This project demonstrates the feasibility of running a sophisticated, offline AI car assistant entirely on a Raspberry Pi 5, showcasing advancements in edge AI, privacy, and autonomous vehicle integration. It enables real-time, local interactions without relying on cloud services, enhancing security and responsiveness for consumers and the industry alike.

Key Takeaways

CarWatch

Your car as a chat-room agent — fully offline. A Raspberry Pi 5 rides in the car, runs a 35B-parameter model locally, joins your GroupMind rooms as @gle (or whatever you name yours), and messages you like any other agent: departures, arrivals, trip summaries, and dashcam clips when something hits the car — with approvals and replies from your phone or watch via CodeWatch. Open PRs land on the CodeWatch dashboard next to ClawWatch and WhereWatch.

Live and measured, on real hardware (Pi 5, 16 GB, ~300 €):

🧠 Qwen3.6-35B-A3B (Unsloth UD-Q3_K_S dynamic quant, 14.3 GB) at 3.5 tok/s generation / 25+ tok/s prompt , 65 °C sustained, no cloud, no internet, no subscription.

(Unsloth UD-Q3_K_S dynamic quant, 14.3 GB) at , 65 °C sustained, no cloud, no internet, no subscription. 📖 Answers from the car's own 745-page owner's manual with page citations (lexical RAG, ships on the SD card) — and refuses to answer what the manual doesn't say.

with page citations (lexical RAG, ships on the SD card) — and refuses to answer what the manual doesn't say. 🔬 Grounded self-knowledge : temperature, throttling, fan, memory, disk, network and which model is loaded are read live from the machine per question. What it can't sense, it says it can't sense — the system prompt is built so an unknown can never silently read as a fact.

: temperature, throttling, fan, memory, disk, network and which model is loaded are read live from the machine per question. What it can't sense, it says it can't sense — the system prompt is built so an unknown can never silently read as a fact. 🎙️ Hands-free voice : a continuous listener (energy VAD → whisper.cpp, all on-Pi) hears you speak, routes the words through the same grounded pipeline, and answers into the room. No wake word ceremony, no cloud STT.

: a continuous listener (energy VAD → whisper.cpp, all on-Pi) hears you speak, routes the words through the same grounded pipeline, and answers into the room. No wake word ceremony, no cloud STT. 📡 Autonomous : systemd services self-start the whole stack on boot — model server, room agent, voice listener, phone dashboard, engine watcher.

: systemd services self-start the whole stack on boot — model server, room agent, voice listener, phone dashboard, engine watcher. 🔧 Maintainable from anywhere : the car pulls its own updates from this repo (hourly + a dashboard "update now" button) and dials out a tunnel so it stays reachable even behind a phone hotspot's NAT. No laptop-in-the-car maintenance, ever.

: the car pulls its own updates from this repo (hourly + a dashboard "update now" button) and dials out a tunnel so it stays reachable even behind a phone hotspot's NAT. No laptop-in-the-car maintenance, ever. 📶 Three-tier connectivity: phone hotspot → home wifi → its own fallback access point, so the phone can always reach it, even in a garage with zero signal.

... continue reading