GLM-OCR

About

What GLM-OCR is

GLM-OCR 👋 Join our <a href="https://raw.githubusercontent.com/zai-org/GLM-OCR/refs/heads/main/resources/wechat.jpg" target="blank"WeChat</a and <a href="https://discord.gg/QR7SARHRxK" target="blank"Discord</a community 📍 Use GLM-OCR's <a href="https://docs.z.ai/guides/vlm/glm-ocr" target="blank"API</a Introduction GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. It introduces Multi-Token Prediction (MTP) loss and stable full-task reinforcement learning to improve training efficiency, recognition accuracy, and generalization. The model integrates the CogViT visual encoder pre-trained on large-scale image–text data, a lightweight cross-modal connector with efficient token downsampling, and a GLM-0.5B language decoder. Combined with a two-stage pipeline of layout analysis and parallel recognition based on PP-DocLayout-V3, GLM-OCR delivers robust and high-quality OCR performance across diverse document layouts. Key Features - State-of-the-Art Performance: Achieves a score of 94.62 on OmniDocBench V1.5, ranking #1 overall, and delivers state-of-the-art results across major document understanding benchmarks, including formula recognition, table recognition, and information extraction. - Optimized for Real-World Scenarios: Designed and optimized for practical business use cases, maintaining robust performance on complex tables, code-heavy documents, seals, and other challenging real-world layouts. - Efficient Inference: With only 0.9B parameters, GLM-OCR supports deployment via vLLM, SGLang, and Ollama, significantly reducing inference latency and compute cost, making it ideal for high-concurrency services and edge deployments. - Easy to Use: Fully open-sourced and equipped with a comprehensive SDK and inference toolchain, offering simple installation, one-line invocation, and smooth integration into existing production pipelines. Performance - Document Parsing & Information Extraction - Real-World Scenarios Performance - Speed Test For speed, we compared different OCR methods under identical hardware and testing conditions (single replica, single concurrency), evaluating their performance in parsing

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys unsloth-glm-ocr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (unsloth-glm-ocr below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"unsloth-glm-ocr","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models