# Microsoft unveils MAI-Base-2 base model with 2 trillion parameters

> The new base model uses a mixture‑of‑experts design and claims up to 12× better hardware efficiency than leading open‑source options.

Oossa · 2026-10-17 · https://oossa.com/en/microsoft-unveils-mai-base-2-base-model-with-2-trillion-parameters

Microsoft’s AI research team announced MAI-Base-2, a 2 trillion‑parameter base model. It uses a mixture‑of‑experts (MoE) architecture that activates only 80 billion neurons per prompt, making it up to 12 times more hardware‑efficient on internal tests. The model was trained for 38 days on 16,000 Nvidia GB200 chips with a 50‑trillion‑token dataset, including a vision component. Microsoft will license the model’s weights to trusted partners via Azure and will build downstream LLMs on top of it.

## The facts

- 2 trillion parameters; activates 80 billion per prompt
- Trained 38 days on 16,000 Nvidia GB200 chips with 50 trillion tokens

## Why it matters

Developers who get access via Azure could build more capable AI services while using less compute power.

## Sources & references

1. [Microsoft reveals cutting-edge MAI-Base-2 model with 2T parameters](https://siliconangle.com/2026/10/16/microsoft-reveals-cutting-edge-mai-base-2-model-with-2t-parameters/) – SiliconANGLE, 2026-10-17

Last updated: 2026-10-17