Rad Dino
Microsoft's Rad Dino is a vision transformer model trained using the self-supervised learning method DINOv2 to encode chest X-rays. It is particularly suited for downstream tasks such as image classification, segmentation, clustering, and retrieval, often achieving good performance without requiring fine-tuning.
Input
Output
Context
-
Max Output
-
Parameters
86.6M
Technical Specifications
Model TypeEmbedding
Context WindowNot available
Max Output TokensNot available
Parameters86.6M
Release DateMay 17, 2024
Training CutoffNot available
LicenseMIT
Open SourceYes
Input Modalities
Image
Output Modalities
Embedding
Capabilities
Resources & Links
Estimated GPU Requirements for Rad Dino
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.