Apple says its most powerful on-device AI model requires an iPhone 17 Pro, iPhone Air, iPad with M4 or later, or a Mac with M3 or later, all with 12GB+ of RAM
Apple’s earlier Apple Intelligence rollout already drew a hardware line: the iPhone 15 Pro and Apple-silicon Macs and iPads were supported, while reporting tied some iPhone exclusions to available RAM. Apple’s M4-family announcements also emphasized expanded memory ceilings and Neural Engine capability.
The newly stated 12GB-plus requirement makes that constraint more explicit for Apple’s highest-end local model. It turns on-device AI capability into a clearer differentiator among recent Apple devices, rather than a broadly uniform software entitlement.
First-order effects
Owners of the specified iPhone 17 Pro, iPhone Air, M4-or-later iPads, and M3-or-later Macs with at least 12GB of RAM can access Apple’s most powerful on-device model; owners of otherwise recent but lower-memory devices cannot.
Apple’s premium-device lineup gains a concrete AI feature boundary tied to processor generation and memory capacity.
Second-order effects
The requirement gives Apple a stronger upgrade rationale for customers whose current devices support some Apple Intelligence features but not the highest-capability local model.
Memory configuration becomes more commercially visible in Apple’s device positioning, while app developers must account for a narrower installed base when designing experiences around the top on-device model.
Third-order effects
If successive AI features continue to carry rising local compute and memory thresholds, Apple’s software roadmap will increasingly segment its installed base by hardware capability and replacement cycle.
The pattern favors a hybrid AI market in which premium devices differentiate through private local execution, while developers and users face more fragmented access to advanced features.
The trend: On-device AI is becoming a hardware-tiering mechanism, with memory and specialized silicon determining which users receive the most capable local models.
Sorry i can really say.. my phone is so old that I can NOT run the most powerful models, I have an 8 months old iPhone... “designed from the ground up for Apple Intelligence” but not the new one :P
🚨 do you understand what happened to Apple.. At WWDC, Apple confirmed that Siri's cloud layer now runs on a custom Google Gemini model with 1.2 trillion parameters, licensed for roughly $1 billion a year. Strategically, this is a reversal. The company that built its brand on [vid…
All Apple Intelligence supported devices get Siri AI The only thing that is device-specific is the new dictation and more expressive voices. The rest is available to all Apple Intelligence devices, including MacBook Neo and iPhone 15 Pro
Further details on how Apple tested these new performance benchmarks: iOS 27 performance testing used an iPhone 11 Pro Max running iOS 26.4.2 vs prerelease iOS 27 Photos loading test used a 50,000-asset library on iPhone 15 AirDrop speed test used 30MB of photos between nearby
Apple Intelligence features are available on iPhone 15 Pro and later, but the most powerful on-device model is limited to newer iPhones, iPads, and Macs. Developers are getting access to Siri AI today, but it is not going to be available in the EU initially. [image]
GGs you need 12GB RAM and an M3/A19 Pro or higher to run the most powerful Apple intelligence on-device model. This is mainly used for Siri's advanced voice, but I believe it could also help speed up image understanding instead of relying on Private Cloud Compute.
Last time around Apple released a lot of information about how their AI version of Siri worked between local and cloud models, not so much this time It is nice to have a Gemma-like model on device, but it is extremely limited unless it can call a smarter cloud model when needed.
Meaning, given the fact that shelf life is one of the things people love about Apple, Siri will remain crap for millions. Guys, do you know how badly you are already losing on your own devices. [embedded post]
What features mandate the “most powerful on-device model” vs. what can be shipped off to the cloud will be interesting to see. In any case, it's all about RAM. Efficiency let Apple cheap out and boost margins for years but there's no way around the need for more where LLMs are …