AI Fundamentals

Mixture of Experts (MoE)

A model architecture where a router network selects a small subset of "expert" sub-networks per token, allowing much larger total parameter counts than are activated per forward pass. Powers frontier models like Mixtral, DeepSeek-R1, and reportedly GPT-4/5. Trades RAM cost for compute cost.

Related terms

Next steps

Where this fits

Mixture of Experts (MoE) is part of the AI Fundamentals vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.