- M5’s 12x neural performance jump marks Apple’s biggest architectural leap
- Dedicated neural accelerators on each GPU core redefine how Apple handles AI processing
- M5 Pro, Max and Ultra Predicted to Dramatically Boost Neural Performance
Apple’s M-series chips have seen regular performance improvements over the past five years, but the jump from the M4 to the M5 stands out the most by far.
The next-generation chip changes the way Apple handles AI workloads, delivering a boost in neural computing that goes far beyond anything seen before on the tech giant’s own silicon.
When Apple’s first chip, the M1, arrived in November 2020, its Neural Engine could handle around 11 trillion operations per second. The M2 brought that figure to just under 16, and the M3 went up to around 18. When the M4 arrived last October, the figure was double that.
Inside Apple Silicon: Part 2 of a five-part series on M-class processors
This article is the second in a five-part series delving into Apple’s M-class processors, from the first M1s to the recently announced M5 and our projected M5 Ultra. Each piece will explore how Apple silicon has evolved in architecture, performance, and design philosophy, and what those changes could mean for the company’s future hardware.
The best of the TOP
With the M5, the number has skyrocketed to approximately 133 TOPS, or about twelve times the M1’s starting point.
That increase is the steepest increase in Apple’s internal processor history. Instead of relying solely on a faster neural engine, the M5 features a dedicated neural accelerator within each GPU core.
This allows graphics hardware to take on AI workloads directly, distributing inference tasks across the chip rather than sending them through a single engine.
The result is a system that handles model-based processes much more efficiently.
Features such as on-device transcription, local imaging, or creative tools that rely on Apple Intelligence benefit from the new structure.
Every part of the chip now contributes to neural processing, and that makes the overall increase in speed seem less like a step and more like a leap.
On paper, the rest of the chip has also improved. The 10-core CPU delivers approximately 15 percent faster multi-threaded performance than the M4 and unified memory bandwidth increases to 153 GB/s. This supports larger models and more efficient multitasking without increasing power usage.
The M5 is inside the new 14-inch MacBook Pro and the new iPad Pro. The tablet version uses a nine- or ten-core CPU, depending on storage, but both share the same Neural Engine and GPU design.
Looking beyond the chips Apple has actually released, the projected numbers for possible future versions give an idea of how far this design could extend.
Estimates from Google Gemini suggest that an M5 Ultra chip could achieve between 600 and 800 TOPS, with the Pro and Max variants between 190 and 320.
None of those chips have been announced (nor has the M4 Ultra; the M3 Ultra was only announced earlier this year and is in Mac Studio) and the numbers are just projections, but they follow the growth pattern seen in previous generations, so they’re on solid footing.
Such increases would inevitably raise family issues. A desktop M5 Ultra would need more cooling and power than Apple’s current compact cases could manage.
What the new M5 shows is that Apple’s chip roadmap is now determined by neural performance rather than raw CPU or GPU power. The company has linked its future Macs and iPads to on-device AI. The next generations will decide how far this can go before physics and thermals catch up.
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
