TechOfficeApple Launches Its Inaugural Official Local AI Event
Apple's First Local AI Event: A Glimpse Into the Future of Memory and On-Device AI
In an unprecedented move, Apple recently hosted its inaugural official local AI event at Apple Park on June 23rd. This gathering marked a significant milestone for the company, with key executives including CEO Tim Cook and hardware chief John Ternus discussing advancements in on-device AI technology and its implications for Apple's product line.
A Focus on Memory Configurations
According to industry insider Alex Cheema, several key presentations during the event alluded to substantial memory configurations, specifically highlighting options of 512GB and 2TB. This indicates that Apple remains committed to providing high-memory options, despite the ongoing global DRAM shortage. Cheema speculates that the forthcoming M5 Ultra chip will feature 512GB of unified memory, while the anticipated M7 Ultra could reach an impressive 1.5TB capacity.
Revelations on Local AI Inference
Citing his attendance at the event, Cheema recreated one notable slide from memory, titled “Enabling a full range of local AI inference.” The slide presented a detailed overview of the memory capacities and active parameters for 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+ |
Future Prospects: Emerging Chips and Capabilities
These developments align with previous reports from Bloomberg's Mark Gurman, who disclosed that Apple is preparing to launch a new AI server based on the M5 Ultra platform (codename J246). Furthermore, Apple is reportedly developing a second-generation server chip rooted in the forthcoming M7 Ultra for release around 2029. Looking even further ahead, an M8 chip (codename "Soko") and a new high-performance Mac chip (codename "Cardinal") are anticipated by 2028, both being designed on a cutting-edge 1.4nm process technology.
Official Confirmation Status
It is crucial to underscore that, as of now, none of this information has been officially confirmed by Apple. The insights shared by Cheema and Gurman provide a tantalizing glimpse into the tech giant's strategic direction in the realm of artificial intelligence and advanced memory configurations.
As Apple continues to innovate within the local AI landscape, industry watchers will be closely monitoring the company's developments as they potentially reshape the computing capabilities available to consumers and professionals alike.
👨🏫 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
