Raspberry Pi AI HAT+ 2  for Raspberry Pi 5  (SC2166) Hailo-10H, 40TOPS (INT4)

Odomknite generatívnu umelú inteligenciu na vašom Raspberry Pi 5

Vďaka novému neurónovému sieťovému akcelerátoru Hailo-10H poskytuje Raspberry Pi AI HAT+ 2 výkon 40 TOPS (INT4) pri inferencii, čím zabezpečuje plynulý chod generatívnych úloh umelej inteligencie na Raspberry Pi 5. AI HAT+ 2 vykonáva všetky AI spracovania lokálne a bez sieťového pripojenia, pracuje spoľahlivo a s nízkou latenciou, pričom zachováva súkromie, bezpečnosť a nákladovú efektívnosť cloudového AI výpočtu, ktorý sme zaviedli s pôvodným AI HAT+. Na rozdiel od svojho predchodcu, AI HAT+ 2 disponuje 8 GB vyhradenej integrovanej pamäte RAM, čo umožňuje akcelerátoru efektívne spracovávať oveľa väčšie modely, ako bolo doteraz možné. To spolu s aktualizovanou hardvérovou architektúrou umožňuje čipu Hailo-10H akcelerovať veľké jazykové modely (LLM), modely videnia a jazyka (VLM) a iné generatívne aplikácie umelej inteligencie. V prípade modelov založených na videní – ako je rozpoznávanie objektov založené na Yolo, odhad polohy a segmentácia scény – je výkon počítačového videnia AI HAT+ 2 vďaka integrovanej pamäti RAM vo veľkej miere ekvivalentný výkonu jeho predchodcu s 26 TOPS. Ďalej ťaží z rovnakej úzkej integrácie s našim softvérovým balíkom pre kamery (libcamera, rpicam-apps a Picamera2) ako pôvodný AI HAT+. Pre používateľov, ktorí už pracujú so softvérom AI HAT+, je prechod na AI HAT+ 2 väčšinou plynulý a transparentný.

The following LLMs will be available to install at launch:

Model	Parameters/size
DeepSeek-R1-Distill	1.5 billion
Llama3.2	1 billion
Qwen2.5-Coder	1.5 billion
Qwen2.5-Instruct	1.5 billion
Qwen2	1.5 billion

More (and larger) models are being readied for updates, and should be available to install soon after launch.

Let’s take a quick look at some of these models in action. The following examples use the hailo-ollama LLM backend (available in Hailo’s Developer Zone) and the Open WebUI frontend, providing a familiar chat interface via a browser. All of these examples are running entirely locally on a Raspberry Pi AI HAT+ 2 connected to a Raspberry Pi 5.

The first example uses the Qwen2 model to answer a few simple questions:

The next example uses the Qwen2.5-Coder model to perform a coding task:

This example does some simple French-to-English translation using Qwen2:

The final example shows a VLM describing the scene from a camera stream:

Fine-tune your AI models

By far the most popular examples of generative AI models are LLMs like ChatGPT and Claude, text-to-image/video models like Stable Diffusion and DALL-E, and, more recently, VLMs that combine the capabilities of vision models and LLMs. Although the examples above showcase the capabilities of the available AI models, one must keep their limitations in mind: cloud-based LLMs from OpenAI, Meta, and Anthropic range from 500 billion to 2 trillion parameters; the edge-based LLMs running on the Raspberry Pi AI HAT+ 2, which are sized to fit into the available on-board RAM, typically run at 1–7 billion parameters. Smaller LLMs like these are not designed to match the knowledge set available to the larger models, but rather to operate within a constrained dataset.

This limitation can be overcome by fine-tuning the AI models for your specific use case. On the original Raspberry Pi AI HAT+, visual models (such as Yolo) can be retrained using image datasets suited to the HAT’s intended application — this is also the case for the Raspberry Pi AI HAT+ 2, and can be done using the Hailo Dataflow Compiler.

Similarly, the AI HAT+ 2 supports Low-Rank Adaptation (LoRA)–based fine-tuning of the language models, enabling efficient, task-specific customisation of pre-trained LLMs while keeping most of the base model parameters frozen. Users can compile adapters for their particular tasks using the Hailo Dataflow Compiler and run the adapted models on the Raspberry Pi AI HAT+ 2.

Available to buy now

The Raspberry Pi AI HAT+ 2 is available now at $130. For help setting yours up, check out our AI HAT guide.

Hailo’s GitHub repo provides plenty of examples, demos, and frameworks for vision- and GenAI-based applications, such as VLMs, voice assistants, and speech recognition. You can also find documentation, tutorials, and downloads for the Dataflow Compiler and the hailo-ollama server in Hailo’s Developer Zone.