MoE

Read news on MoE with our app.

Read more in the app

Thunderobot just launched a laptop that uses a special RAM-like SSD to boost AI performance — AI Master M7000 packs Ryzen AI Max+ 395 with 64GB RAM, runs 120B MoE models

Granite 4.1: IBM's 8B Model Matching 32B MoE

Flash-MoE: Running a 397B Parameter Model on a Laptop

Trinity large: An open 400B sparse MoE model

Nvidia debuts Nemotron 3 with hybrid MoE and Mamba-Transformer to drive efficient agentic AI

Automating Algorithm Discovery: A Case Study in MoE Load Balancing

Sparsely-Gated Mixture of Experts (MoE)