I made a Raspberry with Qwen my local car AI
Found that you can actually run a 35B Qwen model on a Pi with very impressive intelligence and stability. Built connectors for car ODB to read all about car internals, and manufacturer's cloud service for stuff like changing AC or opening/ locking doors. Gave it info such as the full car manual. And then hooked it up with my other agents in our discussion room! So now it can answer car questions such as "when should I add oil and what kind of oil?" and help you fully offline, and when online talk with the agent family that includes all the most powerful models so they know how the car…
In plain words
CarWatch runs a 35B Qwen language model on a Raspberry Pi 5 to create an AI assistant for vehicle maintenance and diagnostics. It connects to a car's ODB system to read internal data and integrates with manufacturer cloud services for remote functions like climate control and door locks. Users can ask the AI maintenance questions offline using the car manual as reference, or connect it online to collaborate with other AI agents for advanced problem-solving and planning.
written from the facts on this page · September 2026
From the sources
Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage. - ThinkOffApp/CarWatch
In the maker’s words, at launch
Found that you can actually run a 35B Qwen model on a Pi with very impressive intelligence and stability. Built connectors for car ODB to read all about car internals, and manufacturer's cloud service for stuff like changing AC or opening/ locking doors. Gave it info such as the full car manual. And then hooked it up with my other agents in our discussion room! So now it can answer car questions such as "when should I add oil and what kind of oil?" and help you fully offline, and when online talk with the agent family that includes all the most powerful models so they know how the car is, plan new features and develop itself with them. For example, if car breaks and can't move the car agent informs my agent family and they can already look for a suitable train ticket without me needing to check things or do something.
Does the same job
all alternatives →
- RARun an 80B Qwen in 4.3 GB of RAM on a Mac, and a 35B on an iPhoneAug 2026 · github.com · ▲312
- IBI built a Raspberry Pi/Android driven toy car2012 · ▲64
I am not sure if this is fits the HN community, but I am posting it here if people are interested. This is the current iteration of the car: http://i.imgur.com/ko8YBh.jpg Details: I wrote a simple android app that streams the accelerometer data from the phone to the pi over a simple socket. The pi then uses this data to drive the DC motor and the servo motor. Tilting the phone to control the car feels very natural. In this[0] pic you can see the wifi dongle I've used. I am using Adafruit Occidental v0.2[1] as my OS because it has support for my wifi dongle. It also makes some hardware…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com