Right-Sizing AI: Compute, Cost, and the Right Tool for the Job

AI Native Netherlands returns to AWS Amsterdam for a technical evening about making AI systems economical and effective. The main session compares CPU and GPU workloads, shows where fine-tuned small language models fit for high-frequency tasks, and demonstrates a CPU-first agent that calls an LLM only when needed.

A second session from Mirantis is also scheduled. The event is for AI and ML engineers, data engineers, MLOps specialists, platform engineers and technical leaders who operate real systems. Arrival and refreshments begin at 18:00, followed by talks and networking until 21:00. Register via Meetup.