the.ai

Weights / Foundations

verified

Merge vs Ensemble

Both take several models and combine them; the difference is when. An ensemble keeps all of them and combines their outputs at every query. A merge combines their weights once and keeps one model. The ensemble is more accurate and the merge is the one you can afford to serve.

Viz primitive · budget-splitensemble-members = 1

ensemble-members holds 50% of the budget; rest holds the remaining 50%.

Inference an ensemble pays on every query, against the single forward pass a merge costs, in models. Drag the member count up to watch the ensemble's recurring cost take everything — the merge's bar never moves, which is the entire argument for it.

1

Reviewed by opendroid · 2026-08-18

  • arXiv:2203.05482 — Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
  • arXiv:2403.13187 — Evolutionary Optimization of Model Merging Recipes