Arm Democratizes On-Device AI: Armv9 Now Available via Flexible Access

Arm has taken a decisive step toward democratizing edge AI development by expanding its Flexible Access program to include the Armv9 platform, offering startups and OEMs low-cost entry to advanced on-device AI capabilities.

A New Era of Accessible AI

The announcement marks a strategic shift in how AI hardware is licensed and deployed. Armv9, the company’s latest architecture, is now available through Flexible Access—a licensing model that allows developers to explore, prototype, and design with Arm IP before committing to full commercial terms.
This expansion includes the Arm Cortex-A320 CPU and the Arm Ethos-U85 NPU, a pairing designed to deliver high-performance AI inference for billion-parameter models while maintaining energy efficiency. The Cortex-A320 will be available in Flexible Access starting November 2025, with the Ethos-U85 following in early 2026.

Fueling Innovation at the Edge

Flexible Access has already seen over 400 tape-outs and boasts 300+ active partners, ranging from early-stage startups to global OEMs. By adding Armv9 to the mix, Arm is enabling a new wave of intelligent edge devices—from wearables and smart cameras to industrial IoT systems.
“Edge AI is no longer a luxury—it’s a necessity,” said Arm’s VP of Product Marketing. “By making Armv9 accessible, we’re empowering innovators to build secure, efficient, and scalable AI solutions without upfront licensing barriers.”

Security Meets Performance

Armv9 introduces robust security features critical for edge deployments, including Pointer Authentication, Branch Target Identification, and Memory Tagging Extension. These architectural enhancements help safeguard devices against runtime attacks and memory corruption, a growing concern in decentralized AI environments.

Strategic Implications

As AI workloads increasingly shift from cloud to edge, Arm’s move positions it as a key enabler of privacy-preserving, low-latency AI. The Flexible Access model also strengthens Arm’s foothold in emerging markets, where cost and agility are paramount.
Industry analysts view this as a competitive play against proprietary chipmakers and cloud-centric AI models. By lowering the barrier to entry, Arm is betting on a future where AI is built into everything—and built by everyone.