All articles tagged with #on device ai
Xiaomi has unveiled the AI Cube engineering prototype, a compact mini PC that combines its Xring O3, O100 and D100 chips to run local AI models up to 120B and 3B with up to 150 W sustained performance, signaling a future where AI workloads run largely on-device; O100 and D100 are planned for commercial launch in 2027 with no price announced.
A hands-on comparison of iPhone 16 and Google Pixel 10 Pro XL finds Google's Pixel offers a far more capable built-in AI photo-editing suite (object removal, reflection fixes, text prompts) than Apple's limited tools, with Pixel delivering better results overall despite occasional missteps; thus, Google is the winner for on-device AI photo editing today.
Apple CEO Tim Cook outlines a hybrid AI approach that runs many tasks on iPhones and Macs to reduce cloud costs, using on-device AI as a competitive edge and monetizing AI through iCloud+ upgrades, with Siri evolving to rely more on-device processing and selective cloud support, and Disney cited as an example of on-device AI workflows that cut cloud spend.
Apple's iOS 27 Developer Beta 4 adds Siri AI to the iPhone 15 Pro/Pro Max, 16, and 17 line, delivering deeper, on‑device conversational responses that aim to close the gap with rivals like Gemini, while highlighting privacy benefits. The beta improves speed and capability but may still cut off prompts at times, with a September stable release anticipated as Apple pushes a more capable AI assistant across its devices.
Apple released iOS 27 beta 4 headlined by a major Siri AI upgrade powered by Apple Intelligence and Foundation Models, delivering richer on‑device conversations, broader AI features across Photos, Safari, Mail and more, plus a Dynamic Island Siri UI. Some features require newer iPhone hardware and on‑device AI capabilities, with on‑device processing limited by devicegen/eligibility; the public release is expected this fall and beta 2 is anticipated soon.
The iOS 27 public beta is now available and supports the same iPhone models that ran iOS 26. It introduces Apple Intelligence and Siri AI features, including a redesigned Siri interface, a standalone Siri app, and new photo-editing tools like Extend and Reframe. A subset of devices with 12GB of RAM — including the iPhone 17 Pro/Pro Max, iPhone Air, and several 16/15 Pro models — will gain access to a more powerful on‑device AI model. Broader updates also touch Messages, FaceTime, Maps, and Music, with a full feature roundup available in the linked article.
Apple is in early talks with PrismML to run compressed AI models directly on iPhones, aiming to move more AI processing on-device to boost speed and privacy while reducing cloud reliance. PrismML’s technique shrinks Alibaba’s Qwen from about 54GB to under 4GB, enabling 27-billion-parameter models to run on iPhone 15+ with 10–15x less memory, 6–8x faster responses, and 3–6x lower energy, though some performance loss is expected. The discussions are not conclusions yet, and real‑world testing (battery impact, reliability, and scale) remains to be proven. Google’s Gemma and larger frontier models are planned next in PrismML’s pipeline, with broader potential beyond phones.)
The Information reports Apple is exploring PrismML’s tech to shrink a 27‑billion-parameter open-source model (Qwen 3.6 from Alibaba) to run directly on an iPhone 17 Pro, enabling on-device AI without servers. PrismML plans to release an open-source model mid-July, and Apple has reportedly held talks with PrismML about using its technology as part of its ongoing, secretive AI efforts.
PrismML says it has compressed Alibaba's Qwen 3.6 into a 27‑billion‑parameter model that runs directly on an iPhone 17 Pro, reportedly the largest on-device AI model to date, highlighting a push toward on-device AI to cut cloud costs and boost privacy, though full technical details are behind a paywall.
Apple’s iOS 27 beta 3 introduces a major Siri AI upgrade powered by Apple Intelligence and Foundation Models, delivering richer conversations, some on-device AI, a Dynamic Island–integrated Siri interface, and broader app integration across the system; however, many features require newer hardware. The release also brings UI refinements (Liquid Glass), performance improvements, and tweaks to Photos, Camera, Messages, and AirPods.
Apple’s Doug Brooks says the Mac mini (and Mac Studio) are in “incredible demand” for running AI agents locally, as developers favor systems that are always on and under user control. He frames agentic AI as a whole‑chip challenge rather than just a GPU one, powered by Neural Engine and other neural accelerators to enable on‑device AI. Brooks envisions a hybrid future where some workloads run locally while others are offloaded to the cloud for privacy and cost reasons, and cites “transparent AI” features on iPhone/iPad and Mac (like Draw Things and SwingVision) as examples of AI quietly working in the background. The interview underscores Apple’s chip‑and‑software approach to push on‑device AI forward, a trend likely to accelerate after WWDC 2026.
Bloomberg’s Mark Gurman says Apple plans two Mac Studio refreshes: an M5 Ultra this year and a more substantial M7 Ultra in 2028, skipping the M6 entirely. The M7 Ultra is expected to feature a redesigned inner architecture and a better heat sink for improved thermals, while the M5 Ultra is not anticipated to have a major redesign. Memory options have been tested up to 768GB, though supply constraints could limit offerings, and launch timing for the M5 remains unclear after delays tied to memory chips and price increases.
Samsung announced UFS 5.0 storage with up to 10.8 GB/s read and 9.5 GB/s write, plus 40% better power efficiency and a smaller package, aimed at accelerating on‑device AI and overall performance. The Galaxy S27 Ultra is rumored to pair this with a 2nm chip, which could make it the first handset to adopt the standard, delivering a snappier experience. Mass production of UFS 5.0 is slated for Q4 2026, signaling a potential competitive edge for the S27 Ultra.
Apple's iOS 27 developer beta introduces an on-device AI dictation system (AFM 3 Core Advanced) with higher accuracy and improved punctuation/casing, but it remains off by default in beta 1 and is limited to newer devices: iPhone 17 Pro/Pro Max, iPhone Air, Vision Pro with M5, iPads with M4+ 12GB RAM, and Macs with M3+ 12GB RAM; the standard iPhone 17 (8GB RAM) is not supported, and it’s unclear if it will be auto-enabled in a future release.
Samsung Electronics announced the industry’s fastest UFS 5.0 storage solution, delivering up to 10.8 GB/s sequential read and 9.5 GB/s write, with more than 40% power efficiency gains versus UFS 4.1, in a compact 7.5 × 13 × 0.9 mm package (16.7% smaller). Mass production starts in Q4 in capacities up to 1 TB, enabling faster on-device AI for next-gen mobile, wearables and XR devices.