Microsoft trains a 2.8T parameter monster
Microsoft just completed pre-training MAI-Base-2, a massive MoE model with 80 billion active and 2.8 trillion total parameters. Trained on 16k GB200 GPUs in 38 days without distillation, it outperforms tested open-weight models and runs 4x to 12x more FLOPs-efficient than DeepSeek-V4-Pro-Base. Why it matters: Microsoft is proving it can build frontier models in-house to license directly to enterprise partners.