Draft page

This page is an outline. It describes what will be covered and is not yet complete technical documentation.

The largest model that fits is rarely the right choice. Model selection sets the floor for your serving cost and the ceiling for your output quality at the same time, and the two pull in opposite directions.

This page frames the decision as an evaluation problem tied to your own task, not a leaderboard comparison.

What you will learn

  • Which model properties actually affect serving cost.
  • How to evaluate candidates against your own task rather than a public benchmark.
  • How licensing and provenance constrain deployment options.
  • When a smaller specialised model beats a larger general one.

This page is an outline. The subsections below are the planned structure; they are filled in as the handbook is written.

Framing the decision

Draft

Capability and task fit

Draft

Size, precision and serving cost

Draft

Context length requirements

Draft

Licensing and provenance

Draft

Building an evaluation set

Draft