IIIF Community Call
Hugging Face
2026-02-11
Daniel van Strien — Machine Learning Librarian @ Hugging Face
| Model | MobileNetV2 — 2.5MB, quantized ONNX |
| Runs | Entirely in your browser via transformers.js |
| Privacy | No data leaves your institution |
| IIIF | Supports Presentation API v2 AND v3 |
| Output | W3C Web Annotations — plugs into your existing infra |
You just saw the model, the dataset, and the tool — all open, all on Hugging Face.
One evening with modern tools turned 3-year-old data into a working browser tool.
An ecosystem of task-specific models built by and for the cultural heritage community.
Data.
Shared datasets and small models are the next layer.
The GLAM sector can build AI infrastructure by building datasets for training and evaluation.
What would help:
The model works well on Western European printed material — we need more diversity.
Daniel van Strien
Links:

IIIF Community Call | Daniel van Strien, ML Librarian @ Hugging Face