Contact →
Catalog · 2026

What we're imagining.

Three artifacts compose the Kōzu lab — fine-tuned models, the apparatus that trains them, and the datasets that shape them.

01/Models

Intelligence, distilled.

SATELLITE CLASSAlpha 4

Deimos A4

A 4.66B reasoning specialist built on Qwen3.5-4B. Internal terse, concise chain-of-thought yields ~60% fewer tokens, ~36% faster inference, and +40 pt avg accuracy on hard math vs base. Distilled from 4,338 shortest-correct traces curated from Deimos-A1.

PLANETARY CLASSPlanned

Europa

Our upcoming medium sized model, designed to explore how intelligence scales per parameter, while further refining the experimental reasoning techniques from Deimos.

STELLAR CLASSPlanned

Ganymede

Our upcoming flagship model — scaling the techniques we've refined into a model tested and validated for real-world scenarios where reasoning efficiency is key.

03/Datasets

Signal, isolated.

REASONINGv0.1

Quark

Our first dataset — built for concise chain-of-thought reasoning (CCoT) and token efficiency. Packs additional reasoning steps inside the same output footprint, so models think further per token instead of spending tokens to think.

COMPLIANCEIn prep

Photon

A compliance-hardening supervised fine-tuning (SFT) dataset family for large language models. Rather than bolting on guardrails at inference time, Photon bakes decision-tree-structured compliance rationales directly into model weights during fine-tuning — making compliant behavior a first-class model capability, not an afterthought. Each domain variant is called an isotope. Isotopes share a common schema and training philosophy but target distinct regulatory and security surfaces.