Apple has announced its new M5, a next-generation system on a chip that the company claims delivers over 4x the peak GPU compute performance for AI compared to M4 through Neural Accelerators integrated into each GPU core.
The chip features a 10-core GPU architecture built using third-generation 3-nanometer technology. Graphics performance reaches up to 45 per cent higher than M4, combining enhanced shader cores with third-generation ray tracing capabilities.
M5 incorporates what Apple describes as the world’s fastest performance core, with up to a 10-core CPU comprising six efficiency cores and up to four performance cores. The configuration delivers up to 15 per cent faster multithreaded performance over M4.
“M5 ushers in the next big leap in AI performance for Apple silicon. 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,” says Johny Srouji, Apple’s senior vice president of Hardware Technologies.
The chip includes an improved 16-core Neural Engine and delivers nearly 30 per cent increased unified memory bandwidth to 153GB/s. The unified memory architecture enables devices to run larger AI models entirely on-device, with 32GB memory capacity supporting simultaneous operation of demanding creative applications.
M5 powers the new 14-inch MacBook Pro, iPad Pro and Apple Vision Pro, all available for pre-order today. The chip delivers over 6x peak GPU compute for AI performance compared to M1, whilst graphics performance reaches up to 2.5x faster than M1.
Apple Vision Pro equipped with M5 renders 10 per cent more pixels through its micro-OLED displays, with refresh rates increasing to 120Hz for reduced motion blur and more fluid display performance.
