Qualcomm collaborates with Meta to empower on-device AI applications through Llama 2

Qualcomm Technologies, Inc. and Meta are collaborating to optimize the on-device execution of Meta’s Llama 2 large language models, eliminating the dependence on cloud services. This enables generative AI models like Llama 2 to run directly on devices such as smartphones, PCs, VR/AR headsets, and vehicles. By doing so, developers can reduce cloud costs while offering users private, reliable, and personalized experiences.

In line with this initiative, Qualcomm Technologies aims to provide on-device Llama 2-based AI implementations, opening up possibilities for the development of innovative AI applications. Customers, partners, and developers can leverage this technology to create intelligent virtual assistants, productivity tools, content creation applications, entertainment, and more. These new on-device AI experiences, powered by Snapdragon®, can function even without connectivity, making them suitable for areas with limited or no internet access, including airplane mode.

Qualcomm and Meta: On-device AI with Llama 2

“We applaud Meta’s approach to open and responsible AI and are committed to driving innovation and reducing barriers-to-entry for developers of any size by bringing generative AI on-device,” said Durga Malladi, senior vice president and general manager of technology, planning and edge solutions businesses, Qualcomm Technologies, Inc. “To effectively scale generative AI into the mainstream, AI will need to run on both the cloud and devices at the edge, such as smartphones, laptops, vehicles, and IoT devices.”

Meta and Qualcomm Technologies have a long history of collaborating to drive technological advancements and provide cutting-edge device experiences. Currently, their joint efforts to support the Llama ecosystem encompass research and product engineering endeavors. Qualcomm Technologies’ prominent position in on-device AI uniquely positions it to contribute to the success of the Llama ecosystem. The company boasts an extensive edge footprint, with billions of devices such as smartphones, vehicles, XR headsets, glasses, PCs, IoT devices, and more, powered by its industry-leading AI hardware and software solutions, thus creating vast potential for the scalability of generative AI.

Starting in 2024, Qualcomm Technologies plans to introduce Llama 2-based AI implementations on devices powered by Snapdragon. To assist developers in optimizing applications for on-device AI, they can utilize the Qualcomm AI Stack—an exclusive set of tools designed to process AI more efficiently on Snapdragon. This capability makes on-device AI feasible even in small, slim, and lightweight devices. To stay informed about the latest updates, developers can subscribe to the monthly newsletter provided by Qualcomm Technologies.