Mixture of Experts (MoE)
Concept
Core Technical
Huge capacity, small bills: only a few experts fire per token.
You're looking at a concept explainer: what this term means in plain English, and the records it ties together.
An MoE model holds many expert sub-networks but routes each token through only a few — DeepSeek-V3 stores 671B parameters yet computes with 37B per token. That decouples capacity from cost and is how open labs reached frontier scale on constrained hardware. The trade: all those parameters still occupy memory, which pushes HBM demand even higher — an architecture choice you can read directly in the memory market.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Basis for
Sources
Record reviewed as of 2026-01-15 — see Methodology.