Subvolts take Arm's hardware makes AI run efficiently on your phone, car, and more, embedding intelligence everywhere. Dec 19, 2025 - Developers
- Learn how Arm's hardware architecture and extensions help balance performance, power, and latency for edge AI applications.
- Business
- Understand how on-device AI is reshaping computing and creating new opportunities across consumer electronics and enterprise solutions.
- Everyday users
- Discover how AI is becoming embedded in everyday devices, making them smarter and more responsive without relying solely on the cloud.
This episode features a key executive from Arm discussing the hardware enabling widespread on-device AI, a significant trend.
#308 Christopher Bergey: How Arm Enables AI to Run Directly on Devices
Audio streams from Craig S. Smith. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Craig Smith hosts Christopher Bergey of Arm on Eye on AI to discuss how AI is moving to devices. They explore how Arm's technology enables on-device AI, the importance of heterogeneous computing, and challenges like memory bandwidth. The conversation covers real-world edge AI applications and a future where AI is embedded in everyday objects, becoming the default interface.
AI is moving from big computers to your phone and gadgets. This episode explains how special chips from Arm make this possible, allowing devices to think faster and use less power. This means smarter devices for everyone.
This episode explains the practicalities of running AI directly on devices, a trend impacting consumer electronics and enterprise solutions. It's for anyone interested in the hardware enabling AI's expansion beyond the cloud, including developers and product designers. This directly relates to frontier labs' efforts to optimize models for diverse hardware, making AI more accessible and efficient across various platforms.
- HostCraig S. Smith
- GuestChristopher BergeyExecutive Vice President, Edge AI Business Unit, Arm
- Guest: Christopher Bergey, Executive Vice President, Arm's Edge AI Business Unit
- Show: Eye on AI
- Episode Length: 52 minutes
- Technology Focus: Arm v9 enables AI inference at the edge
- Key Challenge: Memory bandwidth has become the biggest bottleneck for AI
Try OCI for free at http://oracle.com/eyeonai
This episode is sponsored by Oracle. OCI is the next-generation cloud designed for every workload – where you can run any application, including any AI projects, faster and more securely for less. On average, OCI costs 50% less for compute, 70% less for storage, and 80% less for networking.
Join Modal, Skydance Animation, and today's innovative AI tech companies who upgraded to OCI…and saved.
Why is AI moving from the cloud to our devices, and what makes on device intelligence finally practical at scale?
In this episode of Eye on AI, host Craig Smith speaks with Christopher Bergey, Executive Vice President of Arm's Edge AI Business Unit, about how edge AI is reshaping computing across smartphones, PCs, wearables, cars, and everyday devices.
We explore how Arm v9 enables AI inference at the edge, why heterogeneous computing across CPUs, GPUs, and NPUs matters, and how developers can balance performance, power, memory, and latency. Learn why memory bandwidth has become the biggest bottleneck for AI, how Arm approaches scalable matrix extensions, and what trade offs exist between accelerators and traditional CPU based AI workloads.
You will also hear real world examples of edge AI in action, from smart cameras and hearing aids to XR devices, robotics, and in car systems. The conversation looks ahead to a future where intelligence is embedded into everything you use, where AI becomes the default interface, and why reliable, low latency, on device AI is essential for creating experiences users actually trust.
Stay Updated: Craig Smith on X: https://x.com/craigss Eye on A.I. on X: https://x.com/EyeOn_AI
- Edge AI
- Christopher Bergey
- AI that runs directly on your device, not in the cloud.
- Heterogeneous computing
- Christopher Bergey
- Using different types of processors (CPU, GPU, NPU) together for better performance.
- NPU
- Christopher Bergey
- A specialized processor designed to speed up AI tasks.
- AI inference
- Christopher Bergey
- The process of using a trained AI model to make predictions or decisions.
55 min42 min51 min34 minUkraine's Secret Weapon: The Points System Winning the Drone War | Andrii Hrytseniuk
WithAndrii Hrytseniuk
Questions people ask
- Why is AI moving to devices?
- AI is moving to devices to make on-device intelligence practical at scale, reshaping computing across many types of electronics.
- What is Arm's role in edge AI?
- Arm's v9 architecture enables AI inference directly on devices like smartphones, PCs, and cars, addressing performance, power, and latency challenges.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Craig S. Smith.