Desert Ant Labs: local, fast models that run on device

Re:Desert Ant Labs: local, fast models that run on device by nullbio on Wednesday September 09, 2026 @08:15AM (#49625275)

This is a cool idea. The most useful one for me would be something that can process pdf files into a json schema. Title and tag generation from a post would also be useful. I'm interested in web app though.

[ Parent | on HN ]

Re:Desert Ant Labs: local, fast models that run on device by pveugen on Wednesday September 09, 2026 @09:37AM (#49626362)

OCR on steroids. Our Schemer model will soon be available (free form text to structured JSON). Once that lands, we want to jump into image to JSON.

[ Parent | on HN ]

Re:Desert Ant Labs: local, fast models that run on device by capevace on Wednesday September 09, 2026 @11:03AM (#49627790)

But Schemer will be text-only, correct?

Once image support drops this could be a cool addition to https://struktur.sh. Will it be on OpenRouter too or will all inference have to be self-managed? I’m thinking about server-side use cases, where budgets are low, so small models shine.

edit: ah I saw mainly iOS for now. But an integration would be possible on macOS then, right?

[ Parent | on HN ]

Re:Desert Ant Labs: local, fast models that run on device by pveugen on Wednesday September 09, 2026 @01:42PM (#49630307)

Schemer is text only. But we're working on sort like models for images to data too.

We aim to make all our models available cross-platform. There's a subset currently only iOS/macOS, because they take some more effort to port over to Android and web.

Check out the CLI for easy experimentation: https://github.com/Desert-Ant-Labs/desert-ant-cli#desert-ant...

[ Parent | on HN ]

Re:Desert Ant Labs: local, fast models that run on device by ironsmoke on Wednesday September 09, 2026 @02:01PM (#49630669)

You should check out IBM's Docling.

[ Parent | on HN ]