Apple Hosts Its Inaugural Official Local AI Event

Apple's Inaugural Local AI Event: A Clear Vision for Memory and AI Integration

In a notable advancement in its technological journey, Apple hosted its first-ever official local AI event at Apple Park on June 23rd. This marked a significant moment, as the company’s top executives, including CEO Tim Cook and Vice President of Hardware Engineering John Ternus, addressed the strategic direction of on-device artificial intelligence (AI).

The Highlights of the Event

The private nature of the event meant that detailed insights were shared with a limited audience, but noteworthy information has since surfaced. Reporter Alex Cheema provided an overview of the information presented, emphasizing Apple's robust commitment to high-memory configurations in the face of a global DRAM shortage.

Memory Roadmap Insights

The event featured several slides that highlighted future memory capacities, projecting both 512GB and 2TB configurations. This indicates that Apple is unlikely to forfeit high-memory options, as it continues to strengthen its portfolio of devices aimed at handling complex AI functionalities. Cheema speculates that the upcoming M5 Ultra chip will offer 512GB of unified memory, while the anticipated M7 Ultra may achieve capacities of up to 1.5TB.

Performance Parameters for AI Devices

Cheema painstakingly recreated examples from the event detailing AI performance across various Apple devices. Here’s a summarized table showcasing the projected memory configurations and active parameters:

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+

AI Development and Future Prospects

These findings correspond with reports from Bloomberg's technology analyst Mark Gurman, who has indicated that Apple is working on an AI server based on the M5 Ultra, codenamed J246. This server is expected to pave the way for the next generation of AI chips, including a second-gen server chip based on the future M7 Ultra, projected for release around 2029. Looking even further ahead, the company is said to be developing the M8 chip (codename "Soko") alongside a high-end Mac chip known as "Cardinal," both anticipated to utilize a cutting-edge 1.4nm manufacturing process by 2028.

Conclusion

While Apple has not officially confirmed any of the details emerging from the local AI event, the hints at an enhanced memory roadmap and AI capabilities paint an optimistic picture for tech enthusiasts and industry insiders alike. As the landscape of artificial intelligence continues to evolve, Apple's strategic steps in this direction could redefine the future of on-device computing.

Stay tuned for further updates as Apple continues to innovate within the AI space and expand its hardware capabilities.

👨‍🏫 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