Microsoft finishes pre-training 2.8-trillion-parameter MAI-Base-2

Microsoft AI said it has completed pre-training MAI-Base-2, a mixture-of-experts foundation model with 80 billion active and 2.8 trillion total parameters, trained on 16k GB200 GPUs over 38 days in August and September 2026. Microsoft says its pre-training uses organic data with no distillation from other models, which it says will let it license model weights to trusted partners through Foundry. The model is still in post-training, and no release date was given.

What it means for business: not available yet; data provenance is Microsoft's pitch for enterprise licensing, worth checking when it reaches Foundry.