A Thin Language Model for law. Runs standalone, or as a Lens in front of a frontier model — scoping jurisdiction, citations, and routing before the expensive call.
FR-Lex is designed for two deployment modes: fully standalone on-device, or as a routing layer that scopes and conditions queries before they reach a frontier model.
FR-Lex handles jurisdiction scoping, citation extraction, and query classification — resolving most queries locally, and routing only what needs the frontier model's power.
FR-Lex covers the core reasoning tasks in legal work — jurisdiction, citation, classification, and analysis — without sending client data to a cloud.
Identifies applicable jurisdiction from query context — federal, state, civil, common law — and routes accordingly before any expensive model call.
Extracts and normalises legal citations from unstructured text: case law, statutes, regulations, and secondary sources in major citation formats.
Classifies matters by practice area, urgency, and complexity — enabling paralegal routing, docket prioritisation, and matter-opening automation.
Identifies clauses, flags unusual terms, and extracts key obligations and dates from standard contract structures across common law and civil law templates.
Applies textualist and purposivist lenses to statutory text, surfacing ambiguities and conflicting interpretations with traceable reasoning chains.
Runs entirely on-device. No client communications, case files, or privileged matter data ever leave the machine — compliant by design.
Distilled from frontier legal reasoning into a model that fits on a MacBook. On-device inference for privileged data.
Trained on a proprietary corpus of case law, statutes, regulations, contracts, briefs, and legal commentary — spanning common law and civil law jurisdictions — curated and reviewed by legal domain specialists.
Frontier models with strong legal reasoning serve as teachers. FR-Lex learns the underlying judgment — jurisdiction identification, citation normalisation, clause detection — not surface pattern matching.
Efficient parameter fine-tuning on Apple Silicon via MLX, producing a 4-bit quantized model that runs at inference speeds practical for live legal workflows.
Deploy FR-Lex as a fully independent on-device model, or wire it as a pre-filter in front of a frontier model API. In Lens mode, it conditions the downstream prompt with scoped jurisdiction, extracted citations, and a classified query type — cutting frontier model costs by routing resolved queries locally.
Evaluated on legal domain reasoning tasks. FR-Lex outperforms general-purpose models significantly larger on its target domain.
Download the weights, run it on-device, or wire it as a Lens in front of your frontier model to cut costs and keep client data private.