AllocateWhat is a mixture-of-experts model?
A mixture-of-experts (MoE) model contains many specialist sub-networks but activates only a few per token, so Qwen 3.5 carries 397 billion total parameters but activates about 17 billion per token. This gives frontier-scale capability at mid-size inference cost, which is why most leading 2026 models are MoE.
MoE is the architecture behind the price collapse in open-weight inference: bases like Qwen 3.5 and Kimi K2.5 deliver near-frontier quality while serving at small-model economics.
For buyers, the practical takeaway is to read both numbers: total parameters describe capability ceiling, active parameters describe serving cost.
Compare MoE modelsRelated terms
Allocate is the cloud inference platform for companies that want to train and run their own models.