Siglip 2 So400m Patch 14 384
Google's Siglip 2 So 400M Patch 14 384 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 localization. Its technical architecture incorporates multiple training objectives, including decoder loss and global-local prediction loss, allowing for adaptability in aspect ratio and resolution.
Input
Output
Context
-
Max Output
0K
Parameters
1.1B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Estimated GPU Requirements for Siglip 2 So400m Patch 14 384
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.