At WWDC 2023 today Apple unveiled the M2 Ultra, its most powerful Apple Silicon chip yet. With the M2 Pro and Max launching earlier this year, and rumors pointing to Apple finally bringing the M2 generation to the Mac Studio and Mac Pro, the launch of the Ultra wasn’t a major surprise. In many ways, Apple is following the M1 playbook here, after all, which also had the Ultra chip launch as the highest-end version of the Mac Studio.
Like with the M1 Ultra, the M2 version is also essentially two M1 Max dies fused into a single package. The M1 Ultra featured 20 CPU cores, 64 GPU cores and 32 Neural Engine cores, with support for up to 128GB of unified memory.
The new M2 Ultra, built using 5nm technology and featuring 134 billion transistors, will feature 24 CPU cores, up to 76 GPU cores (there’s also a 60-core option) and a 32-core Neural Engine. The CPU consists of 16 next-gen high-performance cores and eight high-efficiency cores.
One major change, too, here is that the M2 Ultra supports up to 192GB of unified memory, backed by 800GB/s of memory bandwidth.
All of this means the new chip’s CPU performance is up to 20% faster compared to the M1 Ultra and its GPU performance is up 30%, with the Neural Engine now 40% faster than the M1 Ultra’s. That’s enough power to train and run a large language model without a dedicated GPU, Apple says.
The new chip will also be able to support up to six Pro Display XDRs. That’s over 100 million pixels.
“M2 Ultra delivers astonishing performance and capabilities for our pro users’ most demanding workflows, while maintaining Apple silicon’s industry-leading power efficiency,” said Johny Srouji, Apple’s senior vice president of Hardware Technologies. “With huge performance gains in the CPU, GPU, and Neural Engine, combined with massive memory bandwidth in a single SoC, M2 Ultra is the world’s most powerful chip ever created for a personal computer.”