Xclip Base Patch 32
Microsoft's Xclip Base Patch 32 is a vision model capable of general video-language understanding, trained fully-supervised on Kinetics-400. It is genuinely best at tasks like zero-shot, few-shot, or fully supervised video classification and video-text retrieval. Notably, this model was trained using a contrastive approach on video and text pairs, and achieves a top-1 accuracy of 80.4% and a top-5 accuracy of 95.0%.
Input
Output
Context
-
Max Output
-
Parameters
200M
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Resources & Links
Estimated GPU Requirements for Xclip Base Patch 32
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.