Apple today announced the M6 chip, the first built using a 2-nanometer process and featuring a 16-core dual neural engine.
Apple says the 2nm process packs a greater density of transistors into a smaller chip, contributing to the chip’s overall performance and power efficiency gains.
The M6 chip features a larger and more powerful 12-core processor, two more cores than the M5, consisting of two super cores, four performance cores and six efficiency cores. Apple claims the chip delivers the world’s fastest single-threaded performance and multi-threaded performance up to 1.2x faster than the M5, and up to 2.4x faster than the M1.
The chip also has a 12-core GPU, with two more cores than the M5, with a neural accelerator integrated into each core. Apple claims this enables a nearly 30% increase in peak GPU compute for AI compared to the M5, and more than 8x compared to the M1, resulting in rapid processing of prompts for LLMs on the device.
The GPU also benefits from updates to the core shader architecture, dynamic caching and hardware-accelerated ray tracing, as well as a 50% increase in geometry rates for more complex graphics.
The M6 introduces a dual 16-core neural engine, delivering up to 2x the peak computing of previous generations. Apple says system frameworks can automatically use both engines at once, allowing applications to run AI models faster.
The chip supports up to 32 GB of unified memory and up to 170 GB/s of unified memory bandwidth, an increase of 10% over the M5 and 2.5 times more than the M1.
The M6 debuts in the new Mac mini, which launches on Tuesday, September 22.
