TechOfficeApple Unveils Its Inaugural Local AI Event: A New Era of Innovation
Apple’s Inaugural Local AI Event: A Glimpse into the Future of Memory Configurations
In an unprecedented move, Apple has officially hosted its first local AI event at Apple Park, a gathering that has drawn attention not just for its pioneering nature but also for the substantial revelations about the company's memory roadmap. Held on June 23rd, the event saw participation from top executives including CEO Tim Cook and Vice President of Hardware Engineering John Ternus, who shared insights centered around on-device AI solutions.
Memory Roadmap Revealed
According to insights shared by tech analyst Alex Cheema, the event unveiled several key slides indicating Apple’s commitment to high-memory configurations. Despite ongoing challenges within the global DRAM market, Cheema suggests that Apple is not intending to retreat from offering substantial memory options. He predicts that the upcoming M5 Ultra chip will be equipped with 512GB of unified memory, while the highly anticipated M7 Ultra may reach an impressive capacity of 1.5TB.
Key Memory Insights from the Event
While Cheema was unable to reproduce the original slides, he has provided a recreation that highlights the proposed local AI inference capabilities across various Apple devices:
| 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+ |
A Broader AI Strategy
This information corresponds with previous reporting from Bloomberg’s Mark Gurman, who indicated that Apple is in the developmental stages of an AI server based on the M5 Ultra, which carries the codename J246. Looking further into the future, there are plans for a second-generation server chip derived from the M7 Ultra, projected to be ready around 2029. Additionally, Apple is anticipated to introduce an M8 chip, codenamed "Soko," and a high-end Mac chip referred to as "Cardinal," both of which are expected to utilize a cutting-edge 1.4nm process by 2028.
Conclusion
While no official confirmations have been provided by Apple regarding these plans, the details emerging from this local AI event suggest a robust and strategic approach towards enhancing its hardware capabilities, especially in the realm of artificial intelligence. As Apple continues to carve out its niche within this exciting field, industry stakeholders will be keenly watching for upcoming product launches that embody these ambitious designs.
As advancements in both AI and memory technology evolve, Apple’s pioneering efforts at this event offer a sneak peek into a future where high-performance computing may soon become an accessible reality for users around the globe.
👨🏫 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
