MediaTek recently unveiled its latest flagship mobile chip, the Dimensity 9300+, as part of its Dimensity product line. Engineered to deliver enhanced performance, this chip features increased clock speeds and is tailored to expedite on-device generative AI processing, offering broader support for Large Language Models (LLMs) and other performance upgrades compared with its predecessor, the Dimensity 9300.
“The Dimensity 9300+ will help us continue to build a rich ecosystem of generative AI applications thanks to the chip’s broad LLM support and on-device LoRA Fusion,” said JC Hsu, Corporate Senior Vice President at MediaTek. “To enhance these AI experiences, the Dimensity 9300+ offers impressive performance and enhancements to speed up LLM inference, running tokens much faster for a better user experience.”
The Dimensity 9300+ utilises an All-Big-Core design, powered by a 3rd generation TSMC 4nm process. It incorporates one Arm Cortex-X4 core operating at speeds of up to 3.4 GHz, alongside three Cortex-X4 cores and four Cortex-A720 cores. MediaTek’s new NeuroPilot Speculative Decode Acceleration technology enhances AI processing compared to previous generations, enabling the chip to efficiently handle LLMs with up to 13 billion parameters, with scalability reaching up to 33 billion.
In gaming, the Dimensity 9300+ integrates a 2nd generation hardware ray tracing engine paired with an Arm Immortalis-G720 GPU, delivering smooth ray tracing experiences at 60 FPS and console-grade global illumination effects. MediaTek’s HyperEngine technologies, including MediaTek Adaptive Gaming Technology (MAGT) and the Network Observation System (NOS), enhance gaming performance, power efficiency, and network connectivity.
For photography and videography, the chip features MediaTek’s Imagiq 990 ISP, supporting 18-bit RAW processing and AI semantic analysis video engine for advanced videography features. Additionally, MediaTek’s MiraVision 990 enhances smartphone content with advanced AI depth engine technologies.
Dimensity 9300+ is ideal for a wide range of AI applications, offering:
- Support for on-device LoRA Fusion and NeuroPilot LoRA Fusion 2.0 so developers can quickly bring to market new generative AI applications with text, images, music, and more
- Support for the latest LLMs including 01.AI Yi-Nano, Alibaba Cloud Qwen, Baichuan AI, ERNIE-3.5-SE, Google Gemini Nano, and Meta Llama 2 and Llama 3
- ExecuTorch Delegation for ecosystem deployed on-device inferencing
In terms of connectivity, the Dimensity 9300+ incorporates a 5G R16 modem with AI situational awareness, supporting 4CC-CA Sub-6GHz with up to 7Gbps downlink for fast and reliable connectivity in various scenarios.
There’s plenty of other editorial on our sister site, Electronic Specifier! Or you can always join in the conversation by commenting below or visiting our LinkedIn page.
