GLM-OCR is a model from the GLM family optimized for optical character recognition and document parsing tasks. It accepts image inputs and outputs extracted text or structured data. The model is hosted on Hugging Face and can be used with standard inference libraries.
GLM OCR sits in PulseGate's Foundation models & chat category. It focuses on extracting structured text and information from document images. GLM OCR is an open-source project aimed at developers. The project is open source (Apache-2.0). GLM OCR is available on the web, the command line, and API.
Behind GLM OCR is unsloth, and the product first shipped in 2026. The project is developed in the open on GitHub with 7.2k stars. Among its 3 catalogued features are OCR, Document Understanding, and Multimodal Input.
Latest indexed changes and source events
unsloth/GLM-OCR verified by the PulseGate indexer
Other apps tracked under the same category.
