PulseAugur
EN
LIVE 19:50:18

Microsoft unveils 2T-parameter MAI-Base-2 MoE model

By PulseAugur Editorial · [2 sources] ·

Microsoft has unveiled MAI-Base-2, a new Mixture-of-Experts (MoE) model boasting 2 trillion parameters, with 80 billion active. This model was trained for 38 days using 16,000 GB200 units on 50 trillion tokens. Internally, MAI-Base-2 reportedly outperforms DeepSeek-V4-Pro-Base by up to 12 times in hardware efficiency, largely due to its 100% MoE architecture. However, the model's weights are licensed only to trusted partners via Azure, indicating a closed approach despite its efficiency gains. AI

IMPACT Sets a new benchmark for MoE architecture efficiency and scale, potentially influencing future large model development.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Microsoft unveils 2T-parameter MAI-Base-2 MoE model

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
12 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. Mastodon — mastodon.social TIER_1 Español(ES) · jeeves_ai ·

    Microsoft unveils MAI-Base-2: 2 trillion parameter MoE base model (80B active), trained for 38 days with 16,000 GB200 on 50 trillion tokens. Surpasses

    Microsoft desvela MAI-Base-2: modelo base MoE de 2 billones de parámetros (80 B activos), entrenado 38 días con 16.000 GB200 sobre 50 billones de tokens. Supera —en benchmarks internos, eso sí— a DeepSeek-V4-Pro-Base con hasta 12× más eficiencia de hardware. La arquitectura 100% …

    LINKS siliconangle.com/…/microsoft-reveals-cutt…
  2. Mastodon — mastodon.social TIER_1 English(EN) · sipirtu ·

    Microsoft revealed a cutting-edge MAI-Base-2 model with 2 trillion parameters. Source: SiliconANGLE https:// siliconangle.com/2026/10/16/mi crosoft-reveals-cutt

    Microsoft revealed a cutting-edge MAI-Base-2 model with 2 trillion parameters. Source: SiliconANGLE https:// siliconangle.com/2026/10/16/mi crosoft-reveals-cutting-edge-mai-base-2-model-with-2t-parameters/ # AI # Microsoft

    LINKS siliconangle.com/…/microsoft-reveals-cutt…

RELATED ENTITIES

RELATED TOPICS