Siglip 2 So400m Patch 16 256
Google's Siglip 2 So 400M Patch 16 256 is a vision model that excels at tasks such as zero-shot image classification and image-text retrieval, leveraging its unified pretraining objective to improve semantic understanding and dense features. Notably, it employs a training procedure that incorporates decoder loss, global-local and masked prediction loss, and adaptability to aspect ratio and resolution.
Input
Output
Context
1K
Max Output
-
Parameters
1.1B
Technical Specifications
Model TypeVision
Context Window1,024 tokens
Max Output TokensNot available
Parameters1.1B
Release DateFeb 17, 2025
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Image
Output Modalities
Text
Capabilities
Estimated GPU Requirements for Siglip 2 So400m Patch 16 256
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.