Skip to content
The Nexus
DossierENTITY

Mixture of Experts

Coverage of Mixture of Experts in the Nexus archive.

Earliest in view: Apr 30 · 10:31 UTCMost recent: Jun 30 · 00:30 UTC
Co-mentioned in this coverage
LongCat-2.0topic1https://longcat.chat/blog/longcat-2.0/organization1https://news.ycombinator.com/item?id=48727116organization1IBMorganization1Granite 4.1topic1Open Sourcetopic1
Recent coverage
  • TECHNOLOGYJun 30 · 00:30 UTCHACKER NEWS
    LongCat-2.0, a large-scale MoE model with 1.6T total and 48B Active

    LongCat-2.0 is a large-scale Mixture of Experts (MoE) model with 1.6 trillion total parameters and 48 billion active parameters. The article provides links to the model's blog and Hacker News discussion thread.

  • TECHNOLOGYApr 30 · 10:31 UTCHACKER NEWS
    Granite 4.1: IBM's 8B Model Matching 32B MoE

    IBM has open-sourced its Granite 4.1 model, an 8B parameter model that matches the performance of a 32B Mixture of Experts (MoE) model. The release highlights IBM's advancements in efficient AI model development.