Just How Fast Is Apple Silicon?

Can you say, “Ludicrous Speed”?

At WWDC 2020 Apple officially announced what everyone in the industry already knew: that Apple is transitioning the Mac from “Intel Inside” to “Apple Silicon”.

With “Apple Silicon” being the new marketing term for a new generation of processors based on the existing A-series of ARM-based chips that power everything from the iPhone to the iPad to the Apple TV and Apple Watch.

But just how fast is Apple Silicon?

Well, one way of measuring performance is GeekBench 5, which runs a series of benchmarked algorithms on a variety of hardware and which gives a variety of results like single-core performance, multi-core performance, and so on.

The A12Z is an 8-core chip running at 2.48GHz and powers their newest 4th Generation iPad Pro. Let’s look at the performance:

Single Core Performance: 1118, Multi-Core Performance: 4625

These numbers are a bit meaningless by themselves, so let’s compare them to the Geekbench 5 result for a 2020 MacBook Pro 13 model with a 4-core Intel Core i7–1068NG7 and 16 GB of RAM.

Single Core Performance: 1260, Multi-Core Performance: 4676

Not bad for a chip designed for a tablet. Not quite as good in single core, but pretty much on par with the performance delivered by Intel’s 10th-generation four core mobile processor.

But the A12 isn’t the latest generation of Apple’s A-series processors.

The A13 in Apple’s iPhone 11 scores 1327 in single core performance, which puts it close to the speed of an Intel Core i9–9900K running on an iMac. (1351) And that’s clocked at 3.6 GHz as opposed to that of the A13, running at a mere 2.7 GHz.

Of course, many will be quick to point out that the A13 and A12Z can’t keep up that pace as both will soon be throttled down to prevent overheating and to preserve battery life… and they would be absolutely correct in doing so.

But that’s actually one of the key points.

These are the scores that Apple’s A12 and A13 chips post when running on a tablet and on a…

Related posts:

We enjoyed pitching our TeacherBot chatbot powered by Artificial Intelligence to a room of interested investors and technologists at TechCrunch Shanghai 2017.

The goal of a machine learning model is to learn patterns that generalize well on unseen data instead of just memorizing the data that it was trained on. When your model is ready, you would use it to…

Durante un viaggio a Firenze, lo scorso Natale, siamo passati alla libreria indipendente Todo Modo, e pagando alla cassa per un libro illustrato di Iela Mari, ho scambiato due parole con la libraia…