High-performance AI HAT Designed By Raspberry Pi
Built-in Hailo-10H AI Accelerator and 8GB dedicated onboard RAM,
brings generative AI capability to Raspberry Pi 5
| Model | Raspberry Pi AI HAT+ | Raspberry Pi AI HAT+ 2 |
|---|---|---|
| Accelerator chip (Hailo NPU) | Hailo-8L (13 TOPS, INT8) / Hailo-8 (26 TOPS, INT8) |
Hailo-10H (40 TOPS, INT4) |
| Memory (RAM) | Uses the memory on a Raspberry Pi 5 | Has its own 8 GB onboard memory, allowing it to run LLMs and VLMs up to ~6 billion parameters |
| Large Language Model (LLM) support | Not supported | Supported |
| Vision-Language Model (VLM) support | Not supported | Supported |
| Use cases | Object detection, camera post-processing, robotics, moderate neural workloads | Everything available on AI HAT+ plus generative AI workloads, including local LLMs and VLMs |
The Raspberry Pi AI HAT+ 2 is an add-on board based on the Hailo-10H AI accelerator that brings generative AI capability to Raspberry Pi 5. With 8GB of dedicated on-board RAM, the AI HAT+ 2 is ideal for running large language models (LLMs) and vision-language models (VLMs) locally, leaving the host Raspberry Pi 5 free to handle other tasks. The AI HAT+ 2 delivers reliable, low-latency, accelerated generative AI at the edge, making it the perfect choice for applications including offline process control, secure data analysis, facilities management, and robotics.
The AI HAT+ 2 delivers 40 tera-operations per second (TOPS) of INT4 inferencing performance, with computer vision performance equivalent or superior to the 26 TOPS Raspberry Pi AI HAT+. A set of sample models is provided by Hailo; users can also train custom vision models or fine-tune generative AI models using Low-Rank Adaptation (LoRA) to suit their application, such as speech to text, translation, or visual scene analysis.
Like the original Raspberry Pi AI HAT+, the AI HAT+ 2 communicates using Raspberry Pi 5’s PCI Express interface. When the host Raspberry Pi 5 is running an up-to-date Raspberry Pi OS image, it automatically detects the on-board Hailo accelerator and makes it available for AI computing tasks. The built-in rpicam-apps camera applications in Raspberry Pi OS natively support the AI module, automatically using the accelerator to run compatible post-processing tasks.
Key features include:
- Hailo-10H AI accelerator delivering 40 TOPS (INT4) inferencing performance
- Performance for computer vision models comparable to the Raspberry Pi AI HAT+ (26 TOPS)
- Runs generative AI models efficiently using 8GB on-board RAM
- Fully integrated into Raspberry Pi’s camera software stack
- Conforms to Raspberry Pi HAT+ specification
- Supplied with heatsink, and with 16mm stacking header, spacers, and screws to enable fitting on Raspberry Pi 5 with Raspberry Pi 5 Official Active Cooler in place
- Operating temperature: 0°C ~ 50°C (ambient)
With 8GB of dedicated on-board RAM, the AI HAT+ 2 is ideal for running large language models (LLMs) and vision-language models (VLMs) locally, leaving the host Raspberry Pi 5 free to handle other tasks and ensuring your AI models run smoothly.
Delivering reliable, low-latency AI processing at the edge and without a network connection, the AI HAT+ 2 simplifies data security, minimises infrastructure requirements, and reduces cloud API costs.
Raspberry Pi AI HAT+ 2
1x Official Raspberry Pi AI HAT+ 2, Built-in Hailo-10H
