Apple Inc. on Tuesday introduced the M6 chip for the Mac mini and the M5 Ultra for the Mac Studio, both featuring advanced silicon design and AI acceleration capabilities.
The M6 chip, manufactured on a 2-nanometer process, is Apple’s first chip built using this technology. It features a 12-core CPU with two super cores, four performance cores, and six efficiency cores, alongside a 12-core GPU and a dual 16-core Neural Engine. The chip supports up to 32GB of unified memory with 170GB/s bandwidth. Based on Apple’s internal testing in August 2026, the M6 delivers up to 1.2 times faster multithreaded performance than the M5 and up to 2.4 times faster than the M1.
The M5 Ultra, designed for the Mac Studio, uses Apple’s UltraFusion technology to combine two dual-die M5 Max chips into a quad-die architecture. It offers up to 36 CPU cores—12 super cores and 24 performance cores—and up to 80 GPU cores. The chip includes a 32-core Neural Engine, supports up to 512GB of unified memory with 1.2TB/s bandwidth, and features hardware acceleration for H.264, HEVC, four ProRes encode and decode engines, and AV1 decode. Apple’s testing indicates the M5 Ultra achieves up to 1.25 times higher single-threaded and 1.3 times higher multithreaded performance than the M3 Ultra.
Both chips will be available in the latest Mac mini and Mac Studio models. Apple’s vice president of Silicon Engineering Group, Sri Santhanam, said the new chips represent "the next giant leap in performance and AI compute for Apple silicon."
