GoKawiilDeveloper runs Qwen 35B model on Raspberry Pi 5 for offline car assistant CarWatch
A hobbyist built CarWatch, a system that puts a Raspberry Pi 5 in a car running a 35-billion-parameter Qwen model locally, no internet or subscription required. It joins chat rooms as an AI agent, sending trip summaries, dashcam clips, and answers sourced from the car's 745-page owner's manual, and also supports hands-free voice queries via on-device speech recognition.
GoKawiil's interpretation of the reporting above, not reported fact.
The project shows that reasonably large open-weight language models can now run entirely offline on cheap, low-power hardware like a $300 Pi 5, without cloud dependency or ongoing costs. It points to a growing trend of privacy-focused, always-available AI assistants embedded directly into everyday hardware like vehicles.
- Runs a 35B-parameter Qwen model fully offline on a ~€300 Raspberry Pi 5 setup.
- Answers questions using the car's own manual via local retrieval, refusing to guess unknown facts.
- Includes hands-free voice input and live self-diagnostics like temperature and memory usage.
Raspberry Pi 5 16GB Single Board Computer — This is the exact brain behind CarWatch — a Pi 5 with 16GB of RAM is what lets a big quantized Qwen model run entirely offline in the car. It's the go-to board for local LLM tinkering, robotics, and always-on home projects, no cloud or subscription required. Pair it with active cooling and a fast SD card and you can replicate the build this weekend.
See Raspberry Pi 5 16GB Single Board Computer on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: github.com, 2026-08-25
Published there as: “Show HN: I made a Raspberry with Qwen my local car AI”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.