[ modalis — applied-ai lab, toronto ]

Frontier accuracy,on hardware you own.

We train small open models to do one job as well as the frontier, then hand over the whole system: model, adapter, harness, verifier. Small models, trained to one job, as accurate as the frontier. On your machines. Off the meter.

[ scroll — how it works, in 90 seconds ]

Right now, intelligence is something you rent.

one model, rented to millions · the same job, billed every run · your documents make the trip

[ two ways to own it ]

Try the free app. Or have us build one for your business.

[ the free app ]

A filings analyst for your Mac.

An app that reads public company filings. Ask a question across 10-Ks and it answers with the exact numbers, each one quoted and cited to its source sentence. It runs on your laptop and nothing you open ever leaves it.

in development, free at release

get notified at release
[ the engagement ]

The same system, built for your work.

We take the same parts (a small open model, a trained adapter, a harness, a verifier) and build them around your documents and your tasks. Your team signs off on the test it must pass before we train anything. When it passes, you own all of it.

scoped in one working session

book a working session
[ how an engagement runs ]

Test first. Hand over everything.

01

Pick the job

The one you already run through a frontier model on repeat, defined precisely enough to measure.

02

Agree the test first

Your real examples, signed by your stakeholders, before any model runs.

03

Train and harness

A small adapter learns the task at the hub; citations and verification make every answer reviewable.

04

Hand it over

Model, harness, and benchmark land on your machines: seated, versioned, yours. No subscription.

[ start here ]

Bring us the job you repeat.

[ modalis — working session ]
Twenty-five minutes on one job from your business.

Bring the workflow you run through a frontier model on repeat, the one whose bill grows with your volume. We’ll tell you straight whether a small local model can clear the same bar, and what a run costs on hardware you own.

What we cover
  • Whether a small local model can match the frontier model on your job
  • How we would measure that its answers are correct
  • What hardware it needs, what a run costs, and a rough timeline
25 minutes
Google Meet
America/Toronto
[ book directly ]

Tell us about the job.

Send a short note describing the work you want handled and the systems it touches. We will reply with times for a 25-minute session.

email to book