GenAI LLMs runs on Zebra’s devices sans cloud connectivity

Spread the love

Delhi: Zebra Technologies said it has successfully shown GenAI LLMs (Generative Artificial Intelligence large language model (LLM) running on Zebra handheld mobile computers and tablets without needing connectivity to the cloud.

This breakthrough empowers Zebra partners and customers to unlock exciting productivity gains that will shape the future of work across industries from retail to warehouse and logistics to hospitality and healthcare. On-device execution of GenAI LLMs has the potential to empower front-line workers with new capabilities so they can deliver new outcomes for their end customers.

On-device AI can offer additional personalisation and enhanced privacy and security as data remains on the device. It also drives faster performance and lower costs as GenAI searches on the cloud can be expensive. A Qualcomm Technologie’s whitepaper suggests that GenAI-based search cost per query is estimated to increase ten times compared to traditional search methods. By removing the need to utilise the cloud, costs can be reduced.

“Zebra’s devices are powerful platforms with cutting-edge software and AI models which we’re driving forward with our partner ecosystem to solve customer challenges and add value,” said Tom Bianculli, CTO of Zebra Technologies.

“We’re taking GenAI to the mobile edge on-device and applying it to areas such as voice AI, computer vision, and machine vision software powered by deep learning as well as task and workflow software using orchestrated AI,” added Bianculli.

Potential use cases for GenAI LLMs include improving associate effectiveness by enhancing their product and customer service knowledge, acting as an efficient internal communications tool by answering employee queries on things like store policies, collecting and analysing feedback from associates to identify areas of improvement, enhancing productivity and increasing job satisfaction levels.

LLMs also have the potential to elevate the customer experience by powering personalised shopping assistants that could provide product recommendations, integrating shopping experiences across in-store, online, and mobile platforms as well as potentially enabling fully voice-activated shopping.

Zebra’s TC53/TC58 and TC73/TC78 mobile computers and ET6x Series tablets powered by Qualcomm Technologies – together with Zebra’s asset visibility and intelligent automation solutions – deliver elevated data insight, analysis and recommendations, problem-solving, planning and creativity. Front-line workers can utilise a smaller on-device model, even in rural, built-up and underground working environments where connection to the cloud may not be possible. Alternatively, users may switch to a cloud-based app or web browser GenAI tool via Zebra’s Wi-Fi 6/6E and 5G-enabled devices.

“On-device generative AI is unlocking new and enhanced experiences across industries. Qualcomm Technologies’ goal is to drive the transformation of industries, and we are doing that beginning with mobile devices. Zebra’s demonstration showcases the type of transformation we aim to achieve,” said Megha Daga, Senior Director of Product Management, at Qualcomm Technologies.

This innovative solution from Zebra using a platform from Qualcomm Technologies reduces memory requirements. It’s built upon a wide array of open-source and third-party models which are a significant part of Zebra’s strategy to deliver effective on-edge AI solutions across multiple industries.

“Zebra recognizes the importance of ethical and responsible AI,” said Andrea Mirabile, Director of AI Research, at Zebra Technologies.

“We are committed to ensuring our AI initiatives are aligned with federal guidance on accountability, ethical purpose and transparency and help set the standard related to delivering solutions to end-users. We also support the Business Roundtable AI Road Map and policy recommendations for responsible, appropriate, and ethical AI development and deployment,” added Mirabile.
 

Leave a Reply

Your email address will not be published. Required fields are marked *