TechOfficeApple Launches Inaugural Local AI Event, Showcasing Innovations and Future Vision
Apple's First Local AI Event: A New Era for On-Device Intelligence
On June 23rd, Apple held a landmark event at its headquarters, Apple Park, focused on local artificial intelligence (AI). This gathering marked Apple's inaugural venture into the realm of showcasing on-device AI innovations, featuring high-profile executives like CEO Tim Cook and Vice President of Hardware Engineering John Ternus. This event not only underscored Apple's commitment to artificial intelligence but also provided insights into its ambitious memory roadmap, which has significant implications for future products.
A Glimpse into Apple's Memory Roadmap
According to tech journalist Alex Cheema, key slides from the event revealed exciting details regarding memory configurations, signaling that Apple is maintaining its high-memory offerings amid ongoing global DRAM shortages.
Cheema anticipates that the next-generation M5 Ultra chip is expected to ship with 512GB of unified memory, while the highly anticipated M7 Ultra chip could boast configurations reaching up to 1.5TB. This commitment to expansive memory capacities highlights Apple’s drive to enhance local AI capabilities across its range of devices.
Memory Configurations for Various Apple Devices
Cheema also provided a recreation of one influential slide titled "Enabling a Full Range of Local AI Inference," detailing the memory limits and active parameters for several 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+ |
Future of AI Processing with Advanced Chips
Interestingly, this information aligns closely with recent reports from Bloomberg's Mark Gurman, who has indicated that Apple is in the process of preparing an AI server based on the M5 Ultra chip (code-named J246). Furthermore, he mentioned a second-generation server chip based on the M7 Ultra is projected for release around 2029. Looking even further into the future, an M8 chip (code-named "Soko") and a high-end Mac chip (code-named "Cardinal") are anticipated, both potentially operating on a 1.4nm process by 2028.
Conclusion
While Apple has not officially confirmed any of the details from this event, the information shared and its implications for Apple’s product lineup cannot be understated. With memory capacities reaching unprecedented levels and a firm commitment to on-device AI, Apple is clearly positioning itself for a future where intelligent devices become integral to everyday life. As the tech landscape continues to evolve, Apple’s moves in local AI could redefine how users interact with their devices.
👨🏫 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
