Model reference · open weights

Virchow

Virchow is an open-weight embedding model from paige-ai. Virchow (FP32) weighs 1.3 GB; the smallest configuration that runs it is RTX 3060 12 GB.

• Virchow is a self-supervised vision transformer developed by paige-ai for image feature extraction in computational pathology.
• The model has 631M parameters and uses a ViT-H/14 architecture with a 224x224 image size.
• It is licensed under Apache 2.0.

Summary of the paige-ai/Virchow model card, 2026-10-01

Hugging Face ↗