Apple Unveils Groundbreaking Local AI Event, Marking a New Era in Technology

Apple Hosts First Official Local AI Event, Confirms Memory Roadmap

In a significant move towards integrating advanced artificial intelligence capabilities within its product ecosystem, Apple recently conducted its first official local AI event at Apple Park on June 23rd. The event featured high-profile speakers including CEO Tim Cook and Senior Vice President of Hardware Engineering John Ternus, who discussed the company's vision for on-device AI.

Key Highlights from the Event

According to tech journalist Alex Cheema, the event showcased a variety of informative slides that hinted at Apple's commitment to high-memory configurations for its devices. This comes amid ongoing concerns over DRAM shortages which have affected many tech companies.

Cheema indicated that the slides referred to memory configurations of 512GB and 2TB, indicating that Apple is unlikely to abandon high-performance options. His insights suggest that the forthcoming M5 Ultra chip will feature 512GB of unified memory, while the anticipated M7 Ultra could reach up to a remarkable 1.5TB.

Recreated Memory Roadmap

Although Cheema was not permitted to release the original slides, he reconstructed a notable slide titled "Enabling a Full Range of Local AI Inference." The following outlines the expected memory configurations and associated active parameters for various Apple products:

Device	Unified Memory	Active Parameters
iPhone and iPad	Up to 16GB	Up to 14 billion
MacBook Air	Up to 32GB	Up to 35 billion
Mac mini	Up to 64GB	Up to 70 billion
MacBook Pro	Up to 128GB	Up to 120 billion
Mac Studio	Up to 512GB	Up to 480 billion
Mac Studio Cluster	Up to 2TB	1.6 trillion+

Future Chip Developments

Adding further credence to these developments, Bloomberg's Mark Gurman has reported on Apple's plans for future AI infrastructure. Specifically, the company is working on an AI server based on the M5 Ultra, codenamed J246. This chip is expected to pave the way for a second-generation server chip derived from the M7 Ultra, which is targeted for release around 2029. Additionally, there are ambitious plans for an M8 chip codenamed "Soko" and a high-end Mac chip referred to as "Cardinal," both projected to utilize a cutting-edge 1.4nm manufacturing process by 2028.

Official Stance from Apple

It is important to note that these revelations have not been officially confirmed by Apple. As the tech landscape continues to evolve, the speculation surrounding Apple's AI advancements raises anticipation for how these innovations will affect its product lines in the future.

With significant memory upgrades and focused AI initiatives, Apple appears firmly committed to enhancing its devices' capabilities, positioning itself as a formidable player in the AI realm.

p>As the AI landscape unfolds, all eyes will be on Apple to see how these plans materialize in upcoming product launches and technological advancements.

👨‍🏫 Apple held its first-ever official local AI event which is quietly confirmed its memory roadmap. 📰 According to Alex Cheema, Apple hosted a private local AI event at Apple Park on June 23rd — Apple's first event of its kind, with Tim Cook, John Ternus and other execs speaking about on-device AI. 😐 Cheema says several slides referenced 512GB and 2TB memory configurations – a strong signal Apple isn't planning to abandon high-memory options despite the ongoing DRAM shortage. He expects the M5 Ultra to ship with 512GB unified memory, with the rumored M7 Ultra reaching up to 1.5TB. 🧠 He wasn't able to share the original slides, but recreated one from memory –"Enabling a full range of local AI inference": - iPhone and iPad. Up to 16GB unified memory. Up to 14 billion active parameters. - MacBook Air. Up to 32GB unified memory. Up to 35 billion active parameters. - Mac mini. Up to 64GB unified memory. Up to 70 billion active parameters. - MacBook Pro. Up to 128GB unified memory. Up to 120 billion active parameters. - Mac Studio. Up to 512GB unified memory. Up to 480 billion active parameters. - Mac Studio Cluster. Up to 2TB unified memory. 1.6 trillion+ active parameters. 🤔 This lines up with Bloomberg's Mark Gurman, who separately reported Apple is preparing an AI server based on the M5 Ultra (codename J246), a second-gen server chip based on the M7 Ultra for ~2029, and – further out – an M8 chip (codename "Soko") plus a high-end Mac chip ("Cardinal"), both on a 1.4nm process by 2028. P.S. None of this is officially confirmed by Apple. @Apples 👨‍🏫 Apple held its first-ever official local AI event which is quietly confirmed its memory roadmap. 📰 According to Alex Cheema, Apple hosted a private local AI event at Apple Park on June 23rd — Apple's first event of its kind, with Tim Cook, John Ternus and other execs speaking about on-device AI. 😐 Cheema says several slides referenced 512GB and 2TB memory configurations – a strong signal Apple isn't planning to abandon high-memory options despite the ongoing DRAM shortage. He expects the M5 Ultra to ship with 512GB unified memory, with the rumored M7 Ultra reaching up to 1.5TB. 🧠 He wasn't able to share the original slides, but recreated one from memory –"Enabling a full range of local AI inference": - iPhone and iPad. Up to 16GB unified memory. Up to 14 billion active parameters. - MacBook Air. Up to 32GB unified memory. Up to 35 billion active parameters. - Mac mini. Up to 64GB unified memory. Up to 70 billion active parameters. - MacBook Pro. Up to 128GB unified memory. Up to 120 billion active parameters. - Mac Studio. Up to 512GB unified memory. Up to 480 billion active parameters. - Mac Studio Cluster. Up to 2TB unified memory. 1.6 trillion+ active parameters. 🤔 This lines up with Bloomberg's Mark Gurman, who separately reported Apple is preparing an AI server based on the M5 Ultra (codename J246), a second-gen server chip based on the M7 Ultra for ~2029, and – further out – an M8 chip (codename "Soko") plus a high-end Mac chip ("Cardinal"), both on a 1.4nm process by 2028. P.S. None of this is officially confirmed by Apple. @Apples