Apple debuted two new desktop chips on August 25, putting its first 2nm silicon inside the Mac mini and a quad-die design in the Mac Studio.
M6 is Apple’s first 2nm processor. It pairs a 12-core CPU with a 12-core GPU and a Dual 16-core Neural Engine, delivering up to 2.4x the multithreaded performance of M1 and nearly 30 percent more GPU compute for AI than M5. The chip supports up to 32GB of unified memory with 170GB/s of bandwidth.
M5 Ultra is the company’s most powerful M-series chip yet and the first to use a quad-die architecture. UltraFusion links two dual-die M5 Max chips into a single processor with over 4.4TB/s of inter-die bandwidth. It scales to a 36-core CPU, an 80-core GPU with Neural Accelerators, a 32-core Neural Engine, and up to 512GB of unified memory at 1.2TB/s, 50 percent more bandwidth than M3 Ultra.
We are debuting the next giant leap in performance and AI compute for Apple silicon, said Sri Santhanam, Apple’s vice president of Silicon Engineering Group.
The new Mac mini starts with M6, while the Mac Studio offers M5 Max or M5 Ultra. Both systems are positioned for on-device AI workloads, with Apple pointing to the chips’ ability to run large language models with hundreds of billions of parameters entirely in local memory.
