AIMicrosoft AI1h ago
Microsoft unveils MAI-Base-2, a MoE model with 2.8T total and 80B
Microsoft unveils MAI-Base-2, a MoE model with 2.8T total and 80B active parameters, claiming 4x-12x more pretraining FLOPs-efficiency than DeepSeek-V4-Pro-Base
TL;DRMicrosoft released a more efficient large language model using mixture-of-experts architecture.
Why it matters: Efficiency gains could lower AI deployment costs and accelerate adoption across industries.
In June, we announced MAI-Thinking-1, a general-purpose foundation model post-trained on top of MAI-Base-1 with strong reasoning performance.
Read full articleSource: Microsoft AI · Opens in new tab