Siglip So400m Patch 14 384
Google's Siglip So 400M Patch 14 384 is a multimodal model pre-trained on the WebLi dataset at a resolution of 384x384, utilizing the SoViT-400m architecture. It is genuinely best at tasks like zero-shot image classification and image-text retrieval.
Input
Output
Context
-
Max Output
-
Parameters
878M
Technical Specifications
Model TypeVision
Context WindowNot available
Max Output TokensNot available
Parameters878M
Release DateJan 8, 2024
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Image
Output Modalities
Text
Capabilities
Estimated GPU Requirements for Siglip So400m Patch 14 384
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Google
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.