Apple has updated its processors with the new M6, its first 2-nanometer chip, and the M5 Ultra, its most powerful chip to date, with which it claims to make a leap in performance and local artificial intelligence (AI) processing.
Read more On this day, August 26: What happened in the world on a day like today?
The technology company has unveiled the first member of its new family of computer processors, the M6, which is manufactured with a 2-nanometer process, allowing for the integration of a higher density of transistors in a smaller size, thereby improving performance and energy efficiency.
It consists of a twelve-core CPU module (two supercores, four performance cores, and six efficiency cores) that offers improved single-thread and multi-thread performance so that demanding tasks such as image editing, code compilation, new file indexing, and running agentic AI processes execute quickly.
For its part, the GPU consists of twelve cores, each with a Neural Accelerator, which, according to the company, increases the maximum computing capacity for artificial intelligence by almost 30 percent compared to the M5.
It also debuts a dual 16-core Neural Engine that enables greater performance for artificial intelligence processes. With this component, system environments can automatically use both engines simultaneously, allowing apps to run models faster.
The M6 supports up to 32 GB of unified memory to run multiple demanding apps at once and large language models on the device. It also offers up to 170 GB/s of unified memory bandwidth, 10 percent more than the M5.
According to Apple’s Vice President of Chip Engineering, Sri Santhanam, this processor, integrated into the new Mac mini, “offers the ideal balance of performance, energy efficiency, and on-device AI processing.”
M5 Ultra, Apple’s “most powerful” chip
Alongside the M6, Apple has also introduced the M5 Ultra, which it considers its “most powerful chip” to date and which, through the new Mac Studio, is aimed at professionals who need to accelerate workloads that demand maximum CPU, GPU, and unified memory bandwidth performance, such as complex 3D rendering, visual effects, and on-device execution of cutting-edge AI models.
The M5 Ultra uses UltraFusion to connect two dual-die M5 Max chips and form a quad architecture. Together, these low-latency, high-bandwidth interconnects allow the four chips to function as a single unified processor.
The processor features a CPU with up to 36 cores, consisting of twelve supercores and 24 performance cores, offering up to 1.25 times higher single-thread performance and up to 1.3 times higher multi-thread performance compared to the M3 Ultra.
Regarding the GPU, this component integrates up to 80 cores, with a Neural Accelerator in each of them, which multiplies the maximum processing capacity for AI by up to 4.5 times compared to the M3 Ultra.
The M5 Ultra also includes a 32-core Neural Engine and a media engine with hardware-accelerated H.264 and HEVC, four ProRes encode and decode engines, and hardware-accelerated AV1 decode.
Additionally, it offers up to 512 GB of unified memory and 1.2 TB/s of unified memory bandwidth, which is 50 percent more than the M3 Ultra. This allows for storing enormous datasets in local memory, increasing tokens per second speed, and running large language models with hundreds of billions of parameters on the device itself.
- Robots make human records obsolete in China’s robotic sports competition
- “I’d give anything to be like him”: Brad Pitt reveals his great MotoGP idol
- 9/11 victim identified with forensic technique that has helped solve cold cases
