Model reference · open weights

RudolfV-2

RudolfV-2 is an open-weight embedding model from Aignostics. RudolfV-2 (FP32) weighs 2.3 GB; the smallest configuration that runs it is RTX 3060 12 GB.

• RudolfV-2 is a vision transformer foundation model developed by Aignostics for computational pathology and image feature extraction.
• It features a ViT-g/8 backbone with 1.1 billion parameters and was pretrained on whole slide images.
• The model is licensed under CC BY-NC-ND 4.0 with supplementary terms restricting use to academic research and prohibiting clinical or commercial applications.

Summary of the Aignostics/RudolfV-2 model card, 2026-10-01

Hugging Face ↗