stather (v.)

Bench lane

status
active · ongoing
when
2026-08 → now
came from
Marilyn, SnapDragon-Coder, First public repos

Measuring what quantisation and serving stacks actually cost a model, per tier, with the noise floor stated.

Why it started

SnapDragon-Coder died of a quantisation nobody had measured. The lab needed a way to say “this quant costs this much on this kind of task” before trusting a model on a card.

What it is

Benchmark matrices committed as specs, results committed as evidence, run on whichever machine holds the lease. Every tier is reported; an aggregate is not a result. The first programme compared a Qwen3-based coder across quantisation levels and two serving stacks.1

Where it stands

Active. Two findings so far are worth the whole lane: a serving engine’s prompt cache lives in host RAM at about 2.2 GiB per saved 32k slot, which is how a bench machine ran out of memory; and the thinking-budget parameter is charged per round trip, so stacks that batch tool calls differently are not comparable on that axis. See measure the endpoint.2

Lineage

Sources

Numbers on this page are quoted from the lab's own records. The records are private; each note gives the record's date.

  1. lab record, 2026-08-23
  2. lab record, 2026-08-26