Small models, expertly tuned — specialists that beat generalists on the tasks that matter.
The industry's instinct is to reach for the largest model available. Ours is the opposite. By 2026, a well-tuned sub-10-billion-parameter model routinely matches yesterday's frontier models on the narrow task it was trained for — at a fraction of the compute, on hardware you can hold in one hand, inside a power budget a battery can sustain.
Our bet, proven across our deployed platforms: specialisation plus composition beats generalisation — many small experts, each owning one modality or one task, coordinated by a larger reasoner, with the final verdict always committed by deterministic code, never by a model.
Each tuned to its telemetry vocabulary and served where the data is.
Tiny object detectors for the hot perception path, and compact vision-language models for scene reasoning, captioning, and visual diagnostic flags.
Task-specific classifiers on raw IQ streams and spectrograms for modulation recognition and emitter characterisation.
Lightweight signature classifiers for waveforms and spectrograms, from urban soundscapes to unattended ground sensors.
LiDAR and point-cloud perception for mapping, tracking, and change detection.
Small language models for report understanding, structured extraction, and tool-calling agents.
Begin from the strongest open-weight base for the job — never from scratch.
Parameter-efficient fine-tuning (LoRA / QLoRA) keeps the adaptation small, auditable, and cheap to re-issue as the mission changes.
Quantised to the deployment tier (AWQ, GGUF, INT4) to fit its memory and power envelope.
A tiny student distilled from a larger teacher where the hot path demands single-digit-millisecond inference.
Every training corpus passes an anti-poisoning ingestion gate: provenance-checked sources, integrity controls, and documented lineage. Performance is gated against curated, gold-standard evaluation datasets — measured on disaggregated subgroups rather than flattering averages.
In our framework, a model is a form of policy encoding. Every model we ship is versioned, signed, and entered into a chain of evidence; every deployment is reproducible; and drift monitoring runs alongside operational metrics so silent degradation is caught, never discovered. The same lifecycle discipline that governs the rest of the platform under Tangram and Origi.
And a few thousand labelled examples — we'll show you what a specialist can do. Every technique we recommend is one we have fielded on deployed edge hardware.