DATAG 2026 Summer Conference

Enterprises and developers are increasingly faced with a choice: rely on corporate AI services that ship convenience but also data‑exfiltration risk, or host sophisticated models locally for full control and cost predictability. This session walks you through the entire decision‑making pipeline—from hardware sizing to software orchestration—so you can deploy, query, and continuously improve open‑source large language models (LLMs) on‑premise.