EdgeCortix’s SAKURA-II AI Accelerator Brings Low-Power Generative AI to Raspberry Pi 5 and other Arm-Based Platforms
A powerful combination brings Vision Transformers (ViTs) and Multi-modal Models to low-power Arm devices — enabling efficient real-time generative AI at the edge for enterprises and embedded developers.
Tokyo, Japan June 3, 2025 – EdgeCortix® Inc., a leading fabless semiconductor company specializing in energy-efficient Artificial Intelligence (AI) processing at the edge, today announced that its industry leading AI accelerator, SAKURA-II M.2 Module is now available with Arm-based platforms, including Raspberry Pi 5 and AETINA’s Rockchip (RK3588) platform, delivering unprecedented performance and efficiency for edge AI computing applications.
This powerful integration marks a major leap in democratizing real-time Generative AI capabilities at the edge. Designed with a focus on low power consumption and high AI throughput, the EdgeCortix SAKURA-II M.2 module enables developers to run advanced deep learning models directly on compact, affordable platforms like the Raspberry Pi 5 —without relying on cloud infrastructure.
“Bringing our low-power AI acceleration technology to Raspberry Pi 5 users opens the door for innovators and enterprises around the world to build smarter, faster, and more efficient edge AI-driven devices and systems rapidly,” said Dr. Sakyasingha Dasgupta, Founder and CEO of EdgeCortix. “We’re excited to bring real-world Generative AI capabilities to embedded Arm platforms and fuel the next wave of intelligent, autonomous systems as we pioneer the future of the connected intelligent edge.”
“Pairing the Raspberry Pi 5 with EdgeCortix’s SAKURA-II delivers an incredibly efficient and scalable platform for real-time generative AI at the edge”, said Sailesh Chittipeddi, Venture Partner at Novo Tellus Capital Partners and Board Member at both Lantronix and Tessolve. “What’s equally compelling is SAKURA-II’s ability to accelerate a broad range of Arm-based systems, empowering next-gen IOT and edge applications engineers to deploy high-performance AI solutions across diverse applications without the cost or power burden of traditional data center hardware.”
Key Benefits of SAKURA-II with Raspberry Pi5 and other Arm-enabled Platforms:
- Ability to run the latest Gen AI on-device: Run advanced AI models including Vision Transformers, Small Language Models, and Vision Language Models (VLMs) directly on-device, with minimal latency and power draw.
- Optimized for Arm: Seamless offloading of AI workloads from Arm processors allows for balanced performance and efficiency.
Fast time-to-market: Developers can quickly scale from prototypes to production using production-ready SAKURA-II M.2 modules with certified Raspberry Pi 5 and other Arm platforms. - Affordable AI Deployment: SAKURA-II and Raspberry Pi deliver powerful edge AI at a fraction of the cost of traditional solutions—reducing infrastructure needs and enabling cost-efficient scaling.
- Offline, Autonomous AI for SWaP-C-Constrained Environments: Perfect for drones, robotics, smart agriculture, and security—where size, weight, power, and cost limitations demand efficient on-device intelligence.
With these Arm platforms, EdgeCortix is empowering a broad ecosystem of developers and hardware innovators to build cost-effective, production-ready edge AI solutions. Pairing the SAKURA-II M.2 Module’s high-performance acceleration with the accessibility of Raspberry Pi 5 and other Arm-based devices, advanced Generative AI workloads—including ViTs, LLMs, VLMs —can now run efficiently at the edge. This enables both startups and enterprises to deploy intelligent applications without depending on the cloud.
Learn more about EdgeCortix’s Raspberry Pi 5 and other Arm-powered solutions by getting in touch with us here: https://www.edgecortix.com/en/contact-us-about-arm
About EdgeCortix Inc.
EdgeCortix is pioneering the future of the connected intelligent edge. Founded in 2019 with R&D headquarters in Tokyo, Japan, EdgeCortix focuses on energy-efficient AI processing of Generative AI workloads at the edge. The company’s patented, software-first “hardware and software co-exploration” system powers its AI-specific runtime-reconfigurable accelerator, delivering exceptional performance for edge applications in defense, aerospace, smart cities, Industry 4.0, autonomous vehicles, and robotics.
For more information about EdgeCortix, visit https://www.edgecortix.com/en/
Related Semiconductor IP
- Run-time Reconfigurable Neural Network IP
- AI accelerator
- AI Accelerator
- AI Accelerator Specifically for CNN
- Deeply Embedded AI Accelerator for Microcontrollers and End-Point IoT Devices
Related News
- Raspberry Pi Receives Strategic Investment from Arm, Further Extending Long-Term Partnership
- Raspberry Pi Selects Hailo to Enable Advanced AI Capabilities for Raspberry Pi 5
- Arm Drives Next-Generation Performance for IoT with World’s First Armv9 Edge AI Platform
- The Arm Evolution: From IP to Platform for the AI Era
Latest News
- CAST Releases First Dual LZ4 and Snappy Lossless Data Compression IP Core
- Arteris Wins “AI Engineering Innovation Award” at the 2025 AI Breakthrough Awards
- SEMI Forecasts 69% Growth in Advanced Chipmaking Capacity Through 2028 Due to AI
- eMemory’s NeoFuse OTP Qualifies on TSMC’s N3P Process, Enabling Secure Memory for Advanced AI and HPC Chips
- AIREV and Tenstorrent Unite to Launch Advanced Agentic AI Stack