Raspberry Pi’s new add-on board has 8GB of RAM for running gen AI models

Raspberry Pi is launching a new add-on board capable of running generative AI models locally on the Raspberry Pi 5. Announced on Thursday, the $130 AI HAT+ 2 is an upgraded — and more expensive — version of the module launched last year, now offering 8GB of RAM and a Hailo 10H chip with 40 TOPS of AI performance.

Once connected, the Raspberry Pi 5 will use the AI HAT+ 2 to handle AI-related workloads while leaving the main board’s Arm CPU available to complete other tasks. Unlike the previous AI HAT+, which is focused on image-based AI processing, the AI HAT+ 2 comes with onboard RAM and can run small gen AI models like Llama 3.2 and DeepSeek-R1-Distill, along with a series of Qwen models. You can train and fine-tune AI models using the device as well.

A demo shared by Raspberry Pi shows how you can use the add-on board to power an AI model capable of generating a text-based description of a camera stream, as well as answer a question about whether there are any people in the scene. Another shows how you can translate text from French to English with Qwen2.

However, tech YouTuber Jeff Geerling found that a standalone Raspberry Pi 5 with 8GB of RAM generally outperformed the AI HAT+ 2 across the supported models. Geerling links the lower performance to power draw, as the Pi 5 can operate at up to 10 watts, while the AI HAT+ 2 is limited to 3W.

Though the AI HAT+ 2 may be ideal for specific use cases, Geerling notes that the add-on board’s extra 8GB of RAM is “not quite enough to give this HAT an advantage over just paying for the bigger 16GB Pi with more RAM, which will be more flexible and run models faster.” The AI HAT+ released last year, can also handle AI image processing for a cheaper $70 starting price.

Raspberry Pi says more and “larger” AI models “are being readied for updates, and should be available to install soon after launch.”