Skip to main content
  1. Home
  2. Computing
  3. News

As Apple pushes AI in software, the RAM crisis caught up and your gadgets are feeling old

iOS 27 shows where Apple’s AI roadmap is heading, and why 8GB devices are already losing ground.

Add as a preferred source on Google
Computer, Electronics, Tablet Computer
Apple

Apple’s next big AI divide is starting to look less like a software cutoff and more like a memory cutoff. The iOS 27 requirements for Apple’s strongest on-device AI model suggest some devices built for Apple Intelligence won’t run the most capable version locally.

That puts iPhone 17 Pro and iPhone Air in a different class from older Apple Intelligence-ready hardware. Apple has trained buyers to expect long device lifespans, but AI is making the spec sheet harder to ignore again, especially if you’ve been treating RAM as a background detail.

Why is RAM suddenly the dividing line

The key detail is memory. Apple’s strongest on-device AI model for iOS 27 needs at least 12GB of RAM on supported iPads and Macs, with iPhone 17 Pro and iPhone Air named for iPhone support.

That leaves many current Apple Intelligence devices in an awkward middle ground. An 8GB device may still get plenty of AI features, but the heaviest local model could sit outside its reach.

Recommended Videos

For users, the upgrade math changes fast. Processor speed still counts, but RAM is becoming the quieter spec that helps decide whether a device feels ready for Apple’s next AI wave.

What happens when AI moves local

A device can support Apple Intelligence and still miss the best on-device model. That gap shapes the experience, since local processing is tied to the speed, privacy, and hardware-first feel Apple has emphasized around AI.

Private Cloud Compute gives Apple a way to support more devices without putting every task on the device itself. Still, it creates a practical split between what runs on your gadget and what needs help from Apple’s servers.

That’s where 8GB devices start to feel older than their age. They won’t suddenly become useless, but they may stop feeling like the safest bet for whatever Apple adds next.

Why should your next upgrade depend on memory

The practical takeaway is straightforward. If Apple’s AI roadmap matters to you, RAM deserves more attention than it used to.

You’ll want to treat memory as a long-term AI spec, not just a multitasking spec. That means checking RAM alongside chip generation, especially on iPad and Mac, and watching whether more iPhones move beyond 8GB by default.

The next devices Apple ships with more memory will say a lot about where iPhone, iPad, and Mac AI is headed. For now, Apple Intelligence support alone doesn’t tell you the whole story.

Paulo Vargas
Paulo Vargas is an English major turned reporter turned technical writer, with a career that has always circled back to…
Humans actually prefer talking to an AI than a support person, says gas giant as it cuts jobs
British Gas cuts 1,300 support jobs as its CEO points to changing customer habits
Executive, Person, Electronics

Centrica, owner of British Gas, is cutting 1,300 call centre jobs, and its chief executive says changing customer behaviour is the main reason. The company plans to remove 800 roles as part of a “targeted deployment of AI tools,” on top of the 500 cuts announced last month. Customer service teams in Glasgow, Edinburgh, Cardiff, Leicester, Stockport, and Leeds will be affected over the next two years.

Some positions will disappear when employees leave and are not replaced, while the remaining cuts will come through redundancies. Trade unions have warned that Centrica’s AI investment will hand hundreds of human jobs to chatbots.

Read more
Intel just pulled its 14A production schedule forward by a year
Risk production for 14A is now planned for late 2027
Intel Core Ultra Desktop CPU

Intel has moved up the schedule for its next-generation 14A (1.4-nanometer) manufacturing process, giving its foundry turnaround an important new target.

During Intel’s Q2 2026 earnings call, CEO Lip-Bu Tan said 14A risk production for internal products is now planned for the second half of 2027. High-volume production is expected to begin in 2028. This is earlier than the previous timeline, when Intel was expected to begin risk production in 2028 and move to volume production in 2029.

Read more
Gemini Spark is no longer restricted to Google’s priciest Ultra tier
US subscribers on the $20 Pro plan can now try the AI agent, with a wider rollout expected soon.
Gemini Spark mac app

Google AI Pro subscribers are finally getting access to one of the best features Google announced at I/O this May. Gemini Spark is rolling out to US users on the Pro tier, according to a recent post from the official Google Gemini account on X, with other countries expected to follow soon.

Gemini Spark handles tasks while you're away

Read more