TechOfficeApple Hosts Its Inaugural Local AI Event
Apple's First Official Local AI Event Marks a New Era in Memory Roadmap
In an unprecedented move, Apple has held its inaugural local AI event, signifying its strong commitment to advancing on-device artificial intelligence technology. The event took place on June 23rd, 2023, at Apple Park, where company executives, including CEO Tim Cook and hardware chief John Ternus, presented updates and future plans for local AI capabilities.
Key Highlights from the Local AI Event
According to reports from tech analyst Alex Cheema, the event revealed some exciting insights regarding Apple's memory roadmap, particularly regarding high-memory configurations. Despite the ongoing global DRAM shortage, the discussions indicated that Apple is not planning to retreat from offering high-capacity memory options.
Specific details shared during the event suggested that upcoming devices will feature impressive memory capacities:
- **M5 Ultra**: Expected to ship with 512GB of unified memory.
- **M7 Ultra**: Anticipated to support configurations of up to 1.5TB.
Memory Configurations and Active Parameters
Cheema noted multiple configurations showcased during the presentation, which outlined Apple's ambitious plans for various devices. The recreated slide titled "Enabling a full range of local AI inference" highlighted the memory capacities and active parameters for different Apple products:
| Device | Unified Memory | Active Parameters |
|---|---|---|
| iPhone & 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+ |
This significant scaling in memory configurations positions Apple devices favorably in the competitive landscape of AI processing capabilities, catering to the increasing demand for robust on-device AI functionalities.
Future Developments in Apple's Chip Technology
The event's discussions align with prior reports from Bloomberg's tech journalist Mark Gurman. He highlighted that Apple is in the process of developing an AI server based on the M5 Ultra chip, codenamed J246. Further, the company is also working on a second-generation server chip based on the forthcoming M7 Ultra, anticipated for release around 2029.
Additionally, Apple has its sights set on future innovations, with plans for an M8 chip (codename "Soko") and a high-performance Mac chip ("Cardinal"), both expected to utilize a cutting-edge 1.4nm fabrication process, targeted for 2028.
Conclusion
While Apple has not officially confirmed any of these developments, the insights from this local AI event present a compelling vision for the future of on-device AI technology within its ecosystem. With an emphasis on high-memory configurations and ambitious chip development plans, Apple is positioning itself as a formidable player in the realm of artificial intelligence.
As the tech landscape continues to evolve, audiences and industry experts alike will be keenly watching Apple’s next moves in AI and memory technology.
👨🏫 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
