Apple introduces M6 and M5 Ultra for a leap in Mac AI compute
M6 is Apple’s first 2-nanometer Mac chip, with a 12-core CPU, a 12-core GPU with Neural Accelerators, a dual 16-core Neural Engine, and up to 170GB/s of unified memory. M5 Ultra is the first quad-die M-series SoC, joining two dual-die M5 Max chips with next-generation UltraFusion.
On August 25, 2026 Apple introduced M6 and M5 Ultra, calling the pair a big leap in Mac performance and on-device AI compute.
What we know
- M6 is Apple’s first 2nm Mac chip: a 12-core CPU, a 12-core GPU with Neural Accelerators, a dual 16-core Neural Engine, and up to 170GB/s of unified memory.
- M5 Ultra uses next-generation UltraFusion to connect two dual-die M5 Max chips into the first quad-die M-series SoC.
- M5 Ultra scales to a 36-core CPU, an 80-core GPU, 512GB of unified memory, and 1.2TB/s of memory bandwidth.
- Apple said M6 is up to 1.2x faster than M5 in multithreaded CPU work and offers nearly 30% more peak GPU compute for AI.
Takeaways
- M6 is the first 2nm chip Apple has put in a Mac.
- M5 Ultra is the first four-die system-on-a-chip in the M series.
- Apple framed both chips around on-device AI performance.
Source: Apple


