Microsoft Completes Pre-Training of MAI-Base-2, a 2.8T-Parameter Model
Microsoft AI finished pre-training MAI-Base-2, a 2.8-trillion-parameter MoE foundation model it says is 4–12× more compute-efficient than DeepSeek's strongest open base model.
#Azure
2 stories
Microsoft Announces Maia 300, Its Next AI Inference Chip
Microsoft unveiled Maia 300 on Oct 12, 2026: up to 7× Maia 200 rack throughput, ~40% more tokens per megawatt vs leading GPUs, with production deployments in 2027.