Posts tagged with "AI Inference"

Microsoft announced Azure Maia 300 on 12 October 2026 with 288 GB of HBM4, 18 TB/s and a claim of 40% more tokens per megawatt, but the chip that reaches Microsoft Foundry by year end is Maia 200, serving OpenAI and open-weight models in unnamed European regions with no price change. What the silicon transition does and does not change for EU data zone deployments, model choice and your evaluation baseline.