Local AI with GLM OCR inference snap
GLM-OCR is a compact multimodal model developed by Zhipu AI for optical character
recognition (OCR) and document understanding. It is designed to efficiently extract
and interpret text and structured information from images and documents.
Use this snap to quickly install an optimized environment for local inference with GLM-OCR.
The snap includes the following hardware-optimized inference engines:
- cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
- nvidia-gpu: CUDA-enabled GPU acceleration
The most suitable engine is automatically selected based on the available hardware.
Install:
sudo snap install glm-ocr
Run:
glm-ocr
Some accelerators require extra drivers to be usable with this snap:
https://documentation.ubuntu.com/inference-snaps/how-to/setup/drivers/
License:
The GLM-OCR model is provided by Zhipu AI under the MIT license.
The licenses of all the bundled software can be found after installing the snap at
/snap/glm-ocr/current/usr/share/doc.