GLM-OCR GGUF Backup
English | 简体中文 · Also on ModelScope · 42ailab.com
Z.ai's document recognition model: turns the text, tables and formulas in scans and screenshots into editable text.
The model was built by Z.ai (Zhipu AI) and released under MIT. This repository is neither a new model nor our conversion. The GGUF files were converted by ggml-org and published in
ggml-org/GLM-OCR-GGUF. This repository is a byte-for-byte backup of 2 of those files; nothing was modified.
Why a backup
These files lived only under the converter's own account. If that repository is renamed, deleted, or has its files replaced in place, people who depend on it can no longer download the same bytes.
So we keep the original files, unmodified, on our own ModelScope and Hugging Face accounts. File names, sizes and sha256 digests all match the original.
Use
Packaged for 42model: download GLM-OCR from the model library in the desktop app, or run 42model download glm-ocr:1b-q8_0.
Files and license
| File | Role | Size | sha256 |
|---|---|---|---|
GLM-OCR-Q8_0.gguf |
model weights (Q8_0) | 906.4 MiB | 45bc244a6446aff850521dc41f18bc8d7105ad5f0c2c8c28af04e7cc4f4d50b1 |
mmproj-GLM-OCR-Q8_0.gguf |
vision projector (Q8_0) | 462.0 MiB | 9c4b58e33e316ed142eb5dcb41abec3844d3e6e5dc361ffb782c3fa9d175141f |
The digests can be checked one by one against the file pages of the original ggml-org/GLM-OCR-GGUF repository.
Weights are under the upstream MIT license; the full text is in this repository's LICENSE (upstream ships no separate LICENSE file; it contains the License section of the official model card ZhipuAI/GLM-OCR verbatim, plus the MIT text published by the OSI). Credit for the GGUF conversion goes to ggml-org.