Table Transformer Structure Recognition V1.1 All
Microsoft's Table Transformer Structure Recognition V 1.1 All is a vision model designed for table structure recognition, built upon the Transformer-based object detection architecture equivalent to DETR. It is genuinely best at detecting tables in documents, leveraging its pre-training on PubTables1M and FinTabNet datasets. Notably, this model applies layernorm before self- and cross-attention, a distinct technical trait.
Input
Output
Context
-
Max Output
-
Parameters
28.8M
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Resources & Links
Estimated GPU Requirements for Table Transformer Structure Recognition V1.1 All
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.