“Qualcomm has unveiled two new smartphone chips, with its top-tier offering capable of running a 30-billion-parameter mixture-of-experts AI model directly on-device. This marks a significant leap in on-device AI processing power for consumer smartphones. The move signals Qualcomm's push to make powerful generative AI a native smartphone feature rather than a cloud-dependent one.”
Key Takeaways
- Qualcomm launched two new smartphone chips with a strong focus on AI capabilities.
- The flagship chip supports 30B mixture-of-experts models running entirely on-device, no cloud needed.
- On-device execution of large models could enable faster, private, and offline AI features for users.
Qualcomm's flagship smartphone chip can now run powerful 30B AI models locally.
trending_upWhy It Matters
Running a 30B mixture-of-experts model locally on a smartphone chip is a meaningful benchmark shift that puts pressure on Apple, MediaTek, and Google to match on-device AI performance. For developers, this opens the door to building sophisticated generative AI apps that function without internet connectivity, reducing latency and data privacy concerns. For end users, it could mean powerful AI assistants, real-time translation, and image generation that work offline. Watch for major Android OEMs to highlight these chips in flagship devices launching in the coming months.
FAQ
What is a mixture-of-experts model and why does it matter here?
A mixture-of-experts (MoE) model is an AI architecture that activates only a subset of its parameters for each task, making it more efficient than dense models of the same size. Running a 30B MoE model on-device is significant because it delivers high capability with lower computational cost, making it feasible on mobile hardware.
Which smartphones will use these new Qualcomm chips?
Qualcomm's new chips are expected to appear in upcoming flagship Android smartphones from manufacturers such as Samsung, Xiaomi, and OnePlus. Specific device announcements typically follow chip launches by several months.
How does on-device AI differ from cloud-based AI on smartphones?
On-device AI processes data directly on the phone without sending it to remote servers, offering faster response times, offline functionality, and stronger user privacy. Cloud-based AI requires an internet connection and involves potential data exposure to third-party servers.
