GLM-OCR
A multimodal OCR model for reading complex documents and turning images of text into usable text. It targets accurate and fast document understanding.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: Apache-2.0
Overview
GLM-OCR is a multimodal OCR model for understanding complex documents. It combines a visual encoder, a small cross-modal connector and a GLM-0.5B language decoder, and uses a two-stage pipeline of layout analysis followed by parallel recognition. It turns document images into text, including formulas and tables, and can be deployed with vLLM, SGLang or Ollama.
Key features
- Two-stage layout analysis and parallel recognition
- Handles formulas, tables and information extraction
- Only 0.9B parameters
- Deployable with vLLM, SGLang and Ollama
- Aimed at complex tables, code-heavy documents and seals
Best for
Teams that need to read complex real-world documents into text and want a compact model they can host themselves.
- Upstream
- zai-org/GLM-OCR
- Fork on GitHub
- Guo-astro/GLM-OCR
- Upstream stars
- 7.6k
- Category
- Documents, media and content
- Language
- Python
- License
- Apache-2.0
- Forked
- 2026-03-17
- Sync status
- In syncLast synced 2026-11-09
More in Documents, media and content
LuxTTS is a lightweight text-to-speech model for cloning a voice from reference audio and generating clear 48 kHz speech. Use it locally through Python, Colab, or Hugging Face Spaces.
Forked 2026-10-19Last synced 2026-11-09License: Apache-2.0Documents, media and contentGitHub
A self-hosted knowledge base for writing, organizing, searching, and sharing Markdown notes. It supports offline access and team workspaces for personal or collaborative documentation.
Forked 2026-10-19Last synced 2026-11-09License: MITDocuments, media and contentGitHub
Textus is a free, open-source Markdown editor with an AI writing assistant for drafting and editing on macOS, Windows, and Linux.
Forked 2026-10-18Last synced 2026-11-09License: MITDocuments, media and contentGitHub
Clypra is a free, open-source video editor for editing and arranging footage on a frame-accurate timeline. It uses Rust and GPU acceleration for video decoding and rendering.
Forked 2026-10-14Last synced 2026-11-09License: MITDocuments, media and contentGitHub