Apple has launched the M5, showcasing a significant leap in AI performance and advancements in the chip’s design. Built with third-generation 3-nanometer technology, M5 features a 10-core GPU architecture with a Neural Accelerator in each core, enabling over 4x peak GPU compute performance compared to M4. The GPU enhances graphics capabilities with third-generation ray tracing, resulting in a graphics performance up to 45 percent higher than M4.
M5 includes the fastest performance core, comprising six efficiency cores and up to four performance cores, delivering up to 15 percent faster multithreaded performance over M4.1 An improved 16-core Neural Engine and a nearly 30 percent increase in unified memory bandwidth to 153GB/s further enhance the M5. It brings leading power-efficient performance to the new 14-inch MacBook Pro, iPad Pro, and Apple Vision Pro, allowing each device to excel.
“M5 ushers in the next big leap in AI performance for Apple silicon,” said Johny Srouji, Apple’s senior vice president of Hardware Technologies. “With the introduction of Neural Accelerators in the GPU, M5 delivers a huge boost to AI workloads. Combined with a big increase in graphics performance, the world’s fastest CPU core, a faster Neural Engine, and even higher unified memory bandwidth, M5 brings far more performance and capabilities to MacBook Pro, iPad Pro, and Apple Vision Pro.”
With the next-generation GPU architecture in M5, every compute block of the chip is optimized for AI. The 10-core GPU features dedicated Neural Accelerators in each core, providing over 4x peak GPU compute compared to M4, and over 6x for AI performance versus M1. The new 14-inch MacBook Pro and iPad Pro benefit from accelerated processing for AI-driven tasks, such as running diffusion models or large language models locally.
M5’s enhanced GPU and shader cores achieve up to 30% faster graphics performance than M4 and up to 2.5x faster than M1, along with Apple’s third-generation ray-tracing engine, which offers a 45% graphics uplift in compatible apps. This enables smoother gameplay and faster rendering times for complex graphics tasks. Apple Vision Pro now renders 10% more pixels with micro-OLED displays and supports refresh rates up to 120Hz for improved visual performance.
The GPU architecture facilitates seamless integration with Apple’s software frameworks, allowing applications to benefit from immediate performance boosts and enabling developers to enhance their apps using Tensor APIs in Metal 4.
The 16-core Neural Engine in M5 provides exceptional AI performance and energy efficiency, enhancing AI features in Apple Vision Pro, such as transforming 2D photos into spatial scenes and generating Personas. It also improves the speed of on-device AI tools like Image Playground and benefits developers using Apple’s Foundation Models framework.
M5 offers unified memory bandwidth of 153GB/s, a nearly 30 percent increase over M4 and more than 2x over M1. This architecture allows MacBook Pro, iPad Pro, and Apple Vision Pro to run larger AI models on device, fueling faster CPU, GPU, and Neural Engine performance. With 32GB of memory capacity, M5 enables users to run demanding creative suites like Adobe Photoshop and Final Cut Pro simultaneously while uploading large files to the cloud.