About TrendForce News

TrendForce News operates independently from our research team, curating key semiconductor and tech updates to support timely, informed decisions.

[News] Apple Unveils M6, Its First 2nm Chip Built by TSMC, With 30% AI GPU Compute Boost vs. M5


2026-08-26 Consumer Electronics / Semiconductors editor

Apple is pushing its silicon lineup further with new chips aimed at boosting performance and on-device AI capabilities. According to its press release, Apple debuted the M6 in the new Mac mini and the M5 Ultra in the new Mac Studio. NewsPim adds that the M6 is manufactured using TSMC’s 2nm process.

As noted by MoneyWeekly, TSMC is expected to benefit, as the M6’s commercial launch validates N2 yields and mass-production maturity, paving the way for smartphone, HPC, and custom ASIC customers. Meanwhile, Foxconn, which assembles Mac minis and AI servers at its Houston facility, is also set to benefit.

Alongside the chip upgrade, Apple is also raising prices for its latest Mac mini lineup. ZDNet notes that the M6 Mac mini starts at $899, while the M5 Pro model starts at $1,699, both $100 higher than their previous-generation counterparts. Pre-orders begin on August 25, with the official launch scheduled for September 22.

M6 Brings Major CPU, GPU, and AI Upgrades

The M6 features a new 12-core CPU complex, adding two cores over the M5. It combines two super cores, four performance cores, and six efficiency cores, delivering what Apple calls the world’s fastest single-threaded performance. It also offers up to 1.2x faster multithreaded performance than the M5 and up to 2.4x faster performance than the M1.

On the GPU side, the M6 features a 12-core GPU — two more cores than the M5 — with a Neural Accelerator built into each core. It delivers nearly 30% higher peak GPU compute for AI than the M5 and more than 8x that of the M1, significantly accelerating prompt processing for on-device LLMs.

The M6 also supports up to 32GB of unified memory, allowing users to multitask across demanding applications and run LLMs locally for secure and private agentic tasks. Unified memory bandwidth reaches up to 170GB/s, 10% higher than the M5 and 2.5x that of the M1.

Apple Unveils M5 Ultra With Quad-Die Architecture

Alongside the M6, Apple also introduced the M5 Ultra. According to Apple’s press release, the M5 Ultra uses UltraFusion to link two dual-die M5 Max chips, creating a quad-die architecture for the first time in Apple silicon. The technology boosts inter-die bandwidth to more than 4.4TB/s and increases connection density by over 6x. These high-bandwidth, ultra-low-latency interconnects enable all four dies to operate as a single unified processor.

The M5 Ultra also features a CPU with up to 36 cores, including 12 super cores and 24 performance cores. It delivers up to 1.25x faster single-threaded performance and up to 1.3x faster multithreaded performance than the M3 Ultra.

Read more

(Photo credit: Apple)

Please note that this article cites information from AppleNewsPimMoneyWeekly, and ZDNet.


Get in touch with us