A new version of the Raspberry Pi AI HAT+ has been released with enough grunt to run popular generative AI (GenAI) models, including Qwen and DeepSeek.

OMG Ubuntu is a premier destination for Linux enthusiasts and Ubuntu users, offering a blend of news, tutorials, and customization tips for the Ubuntu operating system. Developers can explore Ubuntu desktop features, software recommendations, and system tweaks to enhance their productivity and user experience. Furthermore, OMG Ubuntu showcases the latest developments in the Ubuntu community, including updates on Ubuntu releases, software updates, and community initiatives, fostering a vibrant ecosystem around the popular Linux distribution.

omg! ubuntu!

Raspberry Pi released the AI HAT+ 2, a hardware add-on featuring a Hailo-10H NPU with 40 TOPS performance and 8GB RAM, enabling Raspberry Pi 5 to run generative AI models locally. The board supports LLMs like DeepSeek-R1-Distill, Llama3.2, and Qwen2.5 variants (1-1.5 billion parameters) without cloud connectivity, offering privacy and low-latency benefits. Unlike the first-generation AI HAT+ designed for vision models, this version bridges the generative AI gap while maintaining computer vision capabilities. Priced at $130/£125, it enables on-device AI processing for hobbyists and developers seeking cloud-free AI computing.

Raspberry Pi AI HAT+ 2 Brings Gen AI to Raspberry Pi 5