Apple's M6 & M5 Ultra Chips: A Step Closer to Closing the AI Gap

Apple has strengthened its silicon portfolio with the introduction of the M6 and M5 Ultra chips, designed to accelerate mainstream on-device AI workloads. The M6 is built on a 2-nanometer process and includes a 12-core CPU, 12-core GPU with Neural Accelerators, a Dual 16-core Neural Engine, and up to 170GB/s of unified memory bandwidth.

The M5 Ultra uses a quad-die architecture and offers up to a 36-core CPU, an 80-core GPU, and 1.2TB/s of unified memory bandwidth. The M6 is focused on accelerating mainstream on-device AI, with its Dual 16-core Neural Engine delivering up to twice the peak compute of previous generations.

The M5 Ultra could provide an even bigger boost to Apple's ambitions in advanced AI development, with its GPU providing up to 4.5 times the peak AI compute of M3 Ultra. Configurations with up to 512GB of unified memory and 1.2TB/s of bandwidth can run large language models locally.

Apple faces stiff competition from Alphabet (GOOGL) and Microsoft (MSFT), which are challenging Apple in AI by building broader AI ecosystems that span consumer applications, enterprise software, cloud infrastructure, developer platforms, and autonomous agents.