• The world’s first Armv9 edge AI platform, optimized for IoT and edge AI workloads, will be available through Arm Flexible Access, giving innovators low-cost, easy access to advanced AI performance and security at the edge
• With more than 400 tape-outs and 300 active members, Arm Flexible Access continues to fuel rapid innovation across the ecosystem, helping startups and OEMs accelerate the next generation of intelligent edge devices

The next wave of AI computing innovation will unfold at the edge – in the devices, interfaces, and systems that bring intelligence closer to where data is created. From wearables and AI assistants to smart cameras, connected home devices, and robotics, the real opportunity lies in high-performance, scalable compute that makes these use cases possible.

To truly realize this opportunity, Arm continues to make our technology more accessible to every single company in our ecosystem – from the smallest startups to the world’s leading OEMs – lowering barriers to entry while accelerating time-to-market.

Today, we’re taking the next step in that mission by expanding Arm Flexible Access to include the world’s first Armv9 edge AI platform, optimized for IoT and edge AI workloads.

Lower Barriers, Faster Innovation: The Power of Arm Flexible Access Now Including the Armv9 Edge AI Platform

By adding the Armv9 edge AI platform to Arm Flexible Access, we’re offering the smoothest market entry, lowest cost, and fastest innovation path for any company building AI-capable edge devices. This delivers leading performance and power efficiency with built-in security features, that intelligent edge devices require to scale.

The Armv9 Edge AI Platform – introduced earlier this year – features the ultra-efficient Arm Cortex-A320 CPU and Arm Ethos-U85 NPU to enable on-device AI models with over one billion parameters, alongside advanced Armv9 security technologies, such as Pointer Authentication Code (PAC), Branch Target Identification (BTI), and Memory Tagging Extension (MTE), to protect critical applications and data at the edge.

Combining Armv9 architectural features, such as Scalable Vector Extension 2 (SVE2), for machine learning (ML) performance and the efficiency of Ethos-U85, delivers a powerful foundation for next-generation edge AI applications, such as smart cameras, smart home applications, industrial automation, and advanced human–machine interfaces, that enable smarter, more natural interactions through vision, voice, and gesture. This allows machines to perceive and respond like humans, while keeping inference and data processing securely on-device.

Cortex-A320 will be available through Arm Flexible Access in November 2025, with Ethos-U85 to follow in early 2026.

This latest milestone in Arm Flexible Access marks a vital commitment to edge AI innovation across Arm’s ecosystem. According to VDC Research, by 2028 AI will be the dominant technology used across IoT projects, with the Arm platform already at the center of this transformation.

Arm Flexible Access gives partners up-front, low-cost or no-cost (for qualifying startups) access to a wide range of Arm technology, tools, and resources. The model has proven to be a catalyst for innovation, allowing companies to experiment and iterate designs freely, only paying license fees for the technology they use in final designs. This has powered groundbreaking edge AI technologies from partners including Raspberry Pi, Weeteq, Hailo and SiMa.ai. Over the past five years, around 400 successful tape-outs have been achieved through Arm Flexible Access, with more than 300 active members participating. More than half of these designs target embedded and IoT applications, bringing new intelligence to the edge.

Defining the Edge AI Computing Landscape

Arm’s mission has always been to democratize access to world-leading technology and put innovation in the hands of everyone in our ecosystem. With Armv9 now available through Arm Flexible Access, we’re giving the next generation of innovators access to the most advanced architecture for edge AI and the tools they need to meet the increasing demand for higher performance, enhanced AI capabilities, improved efficiency, and stronger security.