Z.ai publishes GLM-OCR multimodal model on Hugging Face
Z.ai published GLM-OCR on Hugging Face, an image-text-to-text model for OCR tasks. The model supports multiple languages (English, Chinese, French, Spanish, Russian, German, Japanese, Korean), is MIT-licensed, and has an accompanying arXiv paper.
PUBLISHED2026-01-30
OBSERVED2026-08-11
AGE6mo
SOURCES1
Z.ai published GLM-OCR on Hugging Face, an image-text-to-text model for OCR tasks. The model supports multiple languages (English, Chinese, French, Spanish, Russian, German, Japanese, Korean), is MIT-licensed, and has an accompanying arXiv paper.
COMMUNITY
No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.