When we announced the MediaTek Dimensity 9300 and 8300 SoCs late last year, we emphasized the importance of enabling developers and OEMs with the technology needed to provide key Generative AI features, on-device, to end users. We also highlighted the role that these flagship and premium chipsets are taking on to make that happen, including more powerful APUs and MediaTek’s NeuroPilot AI platform.As part of our ongoing investment in creating ecosystems necessary to ensure a strong future for AI, MediaTek and Google have worked together to successfully integrate and optimize Gemini Nano, Google’s Large Language Model (LLM) designed to bring on-device Generative AI to smartphones, so it can run effectively and efficiently on the MediaTek Dimensity 9300 and 8300 chipsets. This effort includes collaboration with Google using MediaTek’s NeuroPilot toolkit and porting Gemini Nano to MediaTek APU to improve performance.
On-device (or edge) Generative AI provides several advantages to developers and users when compared to cloud computing. Some of the benefits include seamless performance, greater privacy, better security and reliability, lower latency, the ability to work in areas with little to no connectivity, and lower operation cost.
MediaTek and Google plan to unveil an APK running on Dimensity 9300 and 8300 to aid developers and OEMs in deploying Gemini Nano applications.
