HeadlinesBriefing favicon HeadlinesBriefing.com

MediaTek Launches Dimensity 9600 Pro: 2nm Flagship Chip

TechPowerUp News •
×

MediaTek, the world's number one provider of mobile chipsets, today announced the launch of the Dimensity 9600 Pro. This flagship SoC achieved a significant technological milestone, adopting the new 2 nm process node; as the first company to announce reaching this threshold, MediaTek is showcasing its leadership in innovation with the Dimensity Pro 9600. With the next generation of silicon now available in the Dimensity lineup, the Dimensity 9600 Pro will enable many transformative capabilities, combining flagship performance and power efficiency with advanced agentic AI experiences.

"AI is central to the smartphone experience, and devices need greater performance, efficiency, and intelligence to keep pace with rapidly evolving user demands," said JC Hsu, corporate senior vice president at MediaTek and general manager of the Wireless Communications Business Unit. "The Dimensity 9600 Pro meets these demands with a Native AI architecture and dual improvement in performance and power efficiency to deliver new agentic AI experiences."

The MediaTek Dimensity 9600 Pro packs a punch, featuring a 2+3+3 All Big Core CPU design which offers faster, more responsive experiences and an impressive 61% reduction in multicore power consumption. This architecture consists of two C2-Ultra cores with clock speeds up to 4.55 GHz, three C2-Pro big cores at 4.35 GHz, and three C2-Pro big cores at 3.1 GHz. Users will enjoy up to 17% higher single-core performance and up to 15% higher multicore performance compared to the previous generation.

The Dimensity 9600 Pro's dual-NPU architecture and Agentic AI Engine are designed to power the next generation of on-device AI, enabling smartphones to perceive, reason and act more intelligently while keeping AI experiences secure. Its second-generation Super Efficient NPU reduces power consumption by 40% for always-on AI, while the NPU 1090 delivers 51% higher LLM prefill performance, 55% higher Token generation per watt, and supports complex on-device applications, including models up to 30B parameters.