Raspberry Pi Launches $130 AI HAT+ 2 with Hailo 10H Processor and 8GB RAM for Local LLM Processing
By
ingve
Kettled twice. Extra chewy, extra trustworthy.
Summary
Raspberry Pi has launched a new $130 AI HAT+ 2 accessory that includes a Hailo 10H AI processor and 8GB of LPDDR4X RAM. This hardware allows the Raspberry Pi to run large language models (LLMs) entirely standalone, freeing up the Pi's CPU and system RAM for other tasks. The Hailo 10H chip operates at a maximum of 3W power consumption and delivers 40 TOPS of INT8 NPU inference performance, plus equivalent 26 TOPS INT4 machine vision performance. While this represents significant AI acceleration capabilities for the Raspberry Pi ecosystem, the article notes practical limitations including the inability to upgrade the Pi's own RAM.
Key quotes
· 4 pulledToday Raspberry Pi launched their new $130 AI HAT+ 2 which includes a Hailo 10H and 8 GB of LPDDR4X RAM.
With that, the Hailo 10H is capable of running LLMs entirely standalone, freeing the Pi's CPU and system RAM for other tasks.
The chip runs at a maximum of 3W, with 40 TOPS of INT8 NPU inference performance in addition to the equivalent 26 TOPS INT4 machine vision performance on the earlier AI HAT with Hailo 8.
In practice, it's not as amazing as it sounds. You still can't upgrade the RAM on the Pi, but at least this way if you do have a need for an AI coprocessor, you don't have to eat up the
You might also wanna read
Raspberry Pi Launches AI HAT+ 2 Add-on Board with 8GB RAM for Local Generative AI
Raspberry Pi has launched the AI HAT+ 2, an upgraded add-on board for the Raspberry Pi 5 that enables local generative AI model execution. T
The Verge·4mo ago
Raspberry Pi Can Run AI Assistants Like OpenClaw, But Needs Cloud LLM for Practical Use
A Raspberry Pi can run an AI assistant like OpenClaw, but it is only practical when paired with a cloud-based LLM. Running it fully locally
raspberrytips.com·1d ago