---
title: "Compact language models: Labs, StrucTime"
description: "Labs trains compact language models from scratch, organised as experts by domain, energy-efficient and designed to run on the device."
canonical: https://structime.com/en/research/language-models/
language: en
last_modified: 2026-10-21
publisher: "AEON Systems (SIREN 993102821)"
source_format: html
---

# We train compact models from scratch.

> Labs trains compact language models from scratch, organised as experts by domain, energy-efficient and designed to run on the device.

Source : https://structime.com/en/research/language-models/
Publisher: AEON Systems (SIREN 993102821) · StrucTime

Labs · Language

The question

## Why start from scratch?

Starting from an existing model means inheriting what it learned and what it forgot. We train from scratch, with our own architecture and code, to stay in control of what the model knows.

With a single machine, the edge comes from the number of experiments: a small model trains in half an hour, and every idea is checked the same day.

How we work

## What guides the choices.

Four principles, held from the first run to the last.

### One expert per domain

A shared trunk is trained first, then one copy per domain, and the copies are merged afterwards. Each expert is retrained without touching the others.

### Rated data

Each dataset gets a public level, measured on a hand-audited sample.

### A classical method to beat

Each model is compared with gradient boosting, a heuristic or an exact algorithm. If it does no better, it has learned nothing.

### Cost is measured

We measure accuracy per parameter and energy per inference, as well as the score.

Limits

## What we do not claim.

### We do not aim for the top of general rankings.

The best small open models have seen trillions of words. Competing with them on everything is not our goal.

### No customer data.

No StrucTime data is used to train or evaluate our models.

### No figures published.

Until a reproducible evaluation is published, with its code, data and protocol, we give neither score nor date.

## The other line.

World models work on systems that change state rather than on text.