Apple Crams Gargantuan AI Models into iPhones with “LLM in a Flash”

Apple is prepping to pack huge AI smarts into iPhones and iPads with a new technique called “LLM in a Flash.” This allows running advanced large language models (LLMs) that exceed a device’s available memory.

LLMs like Ghat GPT contain billions of parameters, demanding beefy GPUs during training. Even efficient models strain mobile hardware, restricting on-device inference. But Apple’s novel memory optimization unlocks phone-powered LLMs with near-PC capabilities.

The key innovation lies in storing LLM parameters in energy-efficient flash storage rather than limited DRAM. Parameters are intelligently loaded to DRAM as needed during inference, cuts down on expensive data transfers while maximizing reuse in memory.

Additional tricks tailored to flash storage’s strengths, like reading parameters in optimally-sized chunks, squeeze extra performance gains. Together, these enable inference for LLMs 2x larger than the available iPhone memory while accelerating speed over naive loading by 4-5x.

This slimmed-down LLM runs laps around stripped-down mobile NLP models today in accuracy and versatility. Soon, you may enjoy iPhone features rivaling Google Assistant without an internet connection?

Don’t expect consumer deployment soon though. Apple must carefully optimize factors like latency, battery drain, and thermals when running monster AI locally. We likely won’t see complex conversational assistants until Apple can deliver a seamless experience.

But “LLM in a Flash” demonstrates Apple’s commitment to on-device intelligence using innovative methods. Rather than cloud reliance, Apple wants iPhones packed with private, smart AI handy in the pocket.

Just as Apple pioneered smartphone computing, its willingness to push boundaries with AI silicon, software optimization, and app integration could soon bring sci-fi-like experiences to iPhones, with all processing securely done on-device.

So while flashy AI concept demos grab headlines today, don’t sleep on Apple’s behind-the-scenes research? Their patient approach to productizing AI could make iPhones the most intelligent, private-by-design personal assistants yet.

Latest

Apple Siri Chief Calls AI Delays “Embarrassing” in Candid Internal Meeting

Apple's ambitious plans for Siri have encountered significant hurdles,...

Apple Mac Studio M3 Ultra vs. M4 Max: Why the Company Skipped the M4 Ultra Chip

Apple's latest Mac Studio launch has left tech enthusiasts...

Redmi K80 Breaks the Mold: Slimmer Design, Massive Battery, and Premium Features

For years, Redmi's approach to its K series lineup...

Xiaomi Modular Optical System: Revolutionary Smartphone Photography with Detachable Lens

Xiaomi's latest innovation might just redefine what we expect...

Newsletter

Don't miss

Apple Siri Chief Calls AI Delays “Embarrassing” in Candid Internal Meeting

Apple's ambitious plans for Siri have encountered significant hurdles,...

Apple Mac Studio M3 Ultra vs. M4 Max: Why the Company Skipped the M4 Ultra Chip

Apple's latest Mac Studio launch has left tech enthusiasts...

Redmi K80 Breaks the Mold: Slimmer Design, Massive Battery, and Premium Features

For years, Redmi's approach to its K series lineup...

Xiaomi Modular Optical System: Revolutionary Smartphone Photography with Detachable Lens

Xiaomi's latest innovation might just redefine what we expect...

Microsoft Majorana 1 Quantum Chip: Unlocking Stable Qubits for Tomorrow Tech

In an industry where progress is often measured in...
Max Hyland
Max Hyland
Long form contributor Apple iPhone, iPad, watch reviews, opinion, editorial

Apple Siri Chief Calls AI Delays “Embarrassing” in Candid Internal Meeting

Apple's ambitious plans for Siri have encountered significant hurdles, according to candid comments from a top executive. Robby Walker, who leads Siri development and...

Apple Mac Studio M3 Ultra vs. M4 Max: Why the Company Skipped the M4 Ultra Chip

Apple's latest Mac Studio launch has left tech enthusiasts scratching their heads. The company's decision to pair the M4 Max alongside the older M3...

Redmi K80 Breaks the Mold: Slimmer Design, Massive Battery, and Premium Features

For years, Redmi's approach to its K series lineup was predictable: release a standard model and a Pro variant with essentially identical physical dimensions...