Running AI Where the Work Happens: The Shift to Local LLMs

Enterprises are rapidly adopting generative AI, but many are facing challenges with cloud‑based approaches - including data privacy concerns, unpredictable costs, latency, and limited control over sensitive information. In response, a growing number of organizations are exploring local LLM strategies, where AI models run directly on AI PCs or edge devices. This shift enables teams to process data entirely within their own environment - reducing dependency on external services while improving responsiveness and maintaining tighter control over enterprise data.

At the same time, advances in AI hardware and software are making it increasingly practical to run LLMs locally, enabling new approaches to productivity, decision‑making, and secure AI adoption. This session will explore how organizations are thinking about local AI in real‑world scenarios - from enabling offline workflows and secure environments, to balancing model flexibility with governance and accuracy. Attendees will examine both the opportunities and trade‑offs of moving AI closer to the user, and how this shift may reshape enterprise expectations for performance, cost efficiency, and trust.

Join Intel and Iternal for an interactive roundtable where we explore real‑world approaches for running AI locally—how teams are managing data privacy, controlling costs, and enabling faster, more reliable AI‑driven workflows at the endpoint, showcasing business outcomes in a ROI driven environment.