Arm offers startups flexible access to its edge AI platform

Arm has announced that its most powerful edge AI platform, Armv9, is now available to startups through its Flexible Access programme.

Essentially a 'try before you buy' model for chip designers, Flexible Access provides companies with low-cost or no-cost (for qualifying startups) access to a broad portfolio of Arm technology, tools, and resources. This allows them to experiment and iterate on designs freely, only paying licensing fees for the technologies they ultimately incorporate into final products.

According to Arm, this approach has already proven to be a significant catalyst for innovation. Over the past five years, it has facilitated approximately 400 successful chip designs, known as tape-outs. Notable companies already leveraging this model include Raspberry Pi, Hailo, and SiMa.ai.

The Armv9 edge AI platform combines the highly efficient Arm Cortex-A320 processor with the Arm Ethos-U85 NPU, which is dedicated to handling demanding AI workloads. Together, they enable the on-device execution of AI models containing over one billion parameters, eliminating the need for a cloud connection.

This technology will fuel the next generation of edge AI applications, such as smart cameras that interpret scenes rather than just record them, smart home devices that adapt to user habits, and robots capable of interaction through vision, voice, and gesture.

Paul Williamson, Senior Vice President and General Manager of the Internet of Things Group at Arm, predicts that the next wave of AI innovation will occur "at the edge—in the devices, interfaces, and systems that bring intelligence closer to where data is generated."

A major advantage of this approach is enhanced privacy and security. By processing data locally, devices can "perceive and respond in human-like ways while keeping inference and data processing securely on the device." This means personal data, such as voice commands, doesn't need to be sent to remote servers. The Armv9 platform further bolsters security with built-in features like Pointer Authentication Code (PAC) and Memory Tagging Extension (MTE) to protect on-device data.

VDC Research forecasts that by 2028, AI will become the "dominant technology used across IoT projects." Arm's technology is "already central to this transformation," and this latest initiative strengthens its position further.

For developers eager to begin working with edge AI, the Arm Cortex-A320 will be accessible through the programme starting November 2025, with the Ethos-U85 AI processor following in early 2026.

See also: NVIDIA GPUs to power Oracle’s next-generation enterprise AI services

Interested in learning more about AI and big data from industry experts? Explore the AI & Big Data Expo, happening in Amsterdam, California, and London. This comprehensive event is part of TechEx and co-located with other leading technology events including the Cyber Security Expo. Click here for more details.

AI News is brought to you by TechForge Media. Discover other upcoming enterprise technology events and webinars here.