#2929th of 33 in Data and scraping for AIFor data and documents, documents and ocr
glm-ocr
0.9B OCR model and SDK that parses documents into Markdown and JSON
- Stars
- 7.6k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Apr 2026
- Language
- Python
5,267 on 3 Apr 20267,567 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
GLM-OCR is a 0.9B-parameter document OCR model (CogViT encoder, GLM-0.5B decoder) paired with a Python SDK. The SDK runs layout analysis with PP-DocLayout-V3, then recognizes regions in parallel and returns Markdown and JSON. It can call the Zhipu hosted API or a self-hosted vLLM, SGLang, Ollama or MLX server, and ships a CLI and a Flask service.
Who it is for: Engineers extracting Markdown or JSON from PDFs and scanned documents
Strengths
- Small 0.9B model; README lists deployment on vLLM, SGLang, Ollama and Apple Silicon via mlx-vlm
- Reports 94.62 on OmniDocBench V1.5, ranked #1 overall by the authors
- CLI, Python API and Flask endpoint (port 5002) with swappable pipeline modules
- Cloud mode needs no GPU; layout model can be placed on CPU or a chosen GPU
Weaknesses
- Self-hosted pipeline needs a separate vLLM or SGLang server plus transformers>=5.3.0
- Hosted mode depends on a Zhipu API key from open.bigmodel.cn
- Code is Apache-2.0 but model is MIT, and PP-DocLayoutV3 adds a third license to follow
What it needs
- GPU optional
- Needs vLLM or SGLang or Ollama (self-hosted), PP-DocLayout-V3, Zhipu MaaS API (cloud mode)
- Models: zai-org/GLM-OCR (BF16)
- port 5002
Quick answers
Is glm-ocr open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run glm-ocr with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does glm-ocr need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Data and scraping for AI
See all 33| Rank | Project | Score |
|---|---|---|
| 1 | mineruDocument parser that converts PDFs, images and Office files to Markdown and JSON | 94 out of 100 |
| 2 | doclingPython library and CLI that converts PDFs, Office files and more into structured text | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 87 out of 100 |
| #4 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 86 out of 100 |
| #5 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 85 out of 100 |