Apple unveils M6 and M5 Ultra for enhanced performance and AI capabilities

Apple has launched two new chips, the M6 and M5 Ultra, offering significant advancements in performance and AI computing. The M6, Apple’s first 2-nanometer chip, is equipped with a 12-core CPU, a 12-core GPU, and a Dual 16-core Neural Engine. The M5 Ultra, featuring a quad-die architecture, stands as Apple’s most powerful chip to date.

The M6 is featured in the latest Mac mini, while the M5 Ultra is used in the new Mac Studio. The M6 chip is designed with a 12-core CPU complex, featuring two super cores, four performance cores, and six efficiency cores, delivering improved single-threaded and multithreaded performance over the M5 and M1. It supports up to 32GB of unified memory and boasts a 170GB/s unified memory bandwidth, enhancing its capacity to manage demanding tasks and AI workloads.

The M5 Ultra chip is crafted for professionals needing high CPU and GPU performance for tasks like 3D rendering and scientific analysis. It utilizes UltraFusion technology to connect two dual-die M5 Max chips, forming a quad-die architecture, which achieves over 4.4TB/s inter-die bandwidth. This chip supports up to a 36-core CPU and an 80-core GPU, significantly boosting graphics and AI processing capabilities.

The new chips are supported by Apple’s developer frameworks such as Core AI and Core ML, allowing developers to leverage the full potential of the Dual 16-core Neural Engine in the M6 and the Neural Accelerators in the M5 Ultra. These frameworks enable running and optimizing AI models locally on Mac devices, enhancing on-device AI performance.