--- title: Introducing the Raspberry Pi AI HAT+ 2: Enhanced AI... description: Raspberry Pi launched the AI HAT+ 2, an edge AI accelerator featuring the Hailo-10H processor with 40 TOPS performance and 8GB RAM. The board enables on-device... canonical: https://daily.dev/posts/introducing-the-raspberry-pi-ai-hat-2-enhanced-ai-capabilities-for-edge-devices-nbjhwdlw3 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing the Raspberry Pi AI HAT+ 2: Enhanced AI Capabilities for Edge Devices | daily.dev og:description: Raspberry Pi launched the AI HAT+ 2, an edge AI accelerator featuring the Hailo-10H processor with 40 TOPS performance and 8GB RAM. The board enables on-device... og:url: https://daily.dev/posts/introducing-the-raspberry-pi-ai-hat-2-enhanced-ai-capabilities-for-edge-devices-nbjhwdlw3 og:image: https://api.daily.dev/og/posts/nbjHwDlw3.png og:image:alt: Introducing the Raspberry Pi AI HAT+ 2: Enhanced AI Capabilities for Edge Devices og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Introducing the Raspberry Pi AI HAT+ 2: Enhanced AI Capabilities for Edge Devices **[Collections](https://daily.dev/sources/collections)** · 2 min read · 1 upvotes · 0 comments ## Summary Raspberry Pi launched the AI HAT+ 2, an edge AI accelerator featuring the Hailo-10H processor with 40 TOPS performance and 8GB RAM. The board enables on-device execution of LLMs like Llama3.2 and Qwen2.5 (1-1.5B parameters) without cloud dependency. Priced at $130, it supports both generative AI and computer vision tasks through Docker-based setup. While the 8GB RAM may limit extensive workloads, pairing with a 16GB Raspberry Pi 5 can enhance capabilities for privacy-focused, low-latency AI applications. ## Content Raspberry Pi has unveiled the AI HAT+ 2, a significant upgrade to its AI accelerator add-on board for Raspberry Pi single board computers. Designed specifically for running generative AI models on edge devices, this new hardware brings an impressive leap in performance and functionality. ### Hardware Specifications The AI HAT+ 2 is powered by the Hailo-10H neural network accelerator, delivering a remarkable 40 TOPS performance and featuring 8GB of onboard RAM. This setup allows for the local execution of larger AI models, such as large language models (LLMs) including DeepSeek-R1-Distill, Llama3.2, and Qwen2.5 variants with parameters ranging from 1 to 1.5 billion. This capability enables users to run these AI models entirely on-device, minimizing the need for cloud services and enhancing privacy and low-latency processing. ### Enhanced Capabilities Unlike its predecessor, which was geared towards camera-based AI tasks with limited functionality, the AI HAT+ 2 can handle more sophisticated AI workloads. While the older model lacked RAM, constraining it to simpler tasks, the current version's ample memory and upgraded hardware bridge the generative AI gap while retaining strong computer vision capabilities. This advancement allows for seamless use not only in AI-enhanced computing but also in applications requiring robust image processing. ### Pricing and Setup Priced at $130 (£125), the AI HAT+ 2 offers valuable features for hobbyists and developers focused on edge computing. Setup process involves installing Hailo software along with Docker, then uploading AI models directly onto the board. Users can choose between a terminal-based interaction and a web UI interface for managing model execution and performance. ### Conclusion and Considerations While the 8GB RAM and 40 TOPS performance provide significant benefits for edge computing, some users might find the memory capacity limited for extensive AI workloads. For those requiring more power, pairing the AI HAT+ 2 with a Raspberry Pi 5 featuring 16GB RAM may deliver enhanced performance without breaking the budget. Nevertheless, the AI HAT+ 2 positions itself as a versatile and powerful tool for those aiming to explore the potential of on-device AI computing. ## Similar posts on daily.dev - [Raspberry Pi's new AI HAT adds 8GB of RAM for local LLMs](https://daily.dev/posts/raspberry-pi-s-new-ai-hat-adds-8gb-of-ram-for-local-llms-kkiq3xn3f) · Jeff Geerling · 1 upvotes · 0 comments --- Tags: [#edge-computing](https://daily.dev/tags/edge-computing), [#hardware](https://daily.dev/tags/hardware), [#llm](https://daily.dev/tags/llm), [#machine-learning](https://daily.dev/tags/machine-learning), [#raspberry-pi](https://daily.dev/tags/raspberry-pi) [View this post on daily.dev](https://daily.dev/posts/introducing-the-raspberry-pi-ai-hat-2-enhanced-ai-capabilities-for-edge-devices-nbjhwdlw3) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing the Raspberry Pi AI HAT+ 2: Enhanced AI Capabilities for Edge Devices","url":"https://daily.dev/posts/introducing-the-raspberry-pi-ai-hat-2-enhanced-ai-capabilities-for-edge-devices-nbjhwdlw3","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-the-raspberry-pi-ai-hat-2-enhanced-ai-capabilities-for-edge-devices-nbjhwdlw3"},"datePublished":"2026-01-15T11:55:33.755Z","dateModified":"2026-03-15T03:34:11.981Z","description":"Raspberry Pi launched the AI HAT+ 2, an edge AI accelerator featuring the Hailo-10H processor with 40 TOPS performance and 8GB RAM. The board enables on-device...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1a00da7ab585d374b51cffd3b2a74329?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1a00da7ab585d374b51cffd3b2a74329?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-the-raspberry-pi-ai-hat-2-enhanced-ai-capabilities-for-edge-devices-nbjhwdlw3","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"edge-computing,hardware,llm,machine-learning,raspberry-pi","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"Introducing the Raspberry Pi AI HAT+ 2: Enhanced AI Capabilities for Edge Devices"}]} ```