Z.ai · First MLX build 3 Feb 2026
GLM-OCR
MLX
Vision mit
A 1.1B parameter image to text model from Z.ai, with one MLX build at bf16.
- Parameters
- 1.1B From Hugging Face
- Quantisation
- bf16 GLM-OCR-bf16
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.2 GB Weights, estimated
- Downloads
- 2.6K This build, last 30 days
- Task
- Image to text Vision
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 5 GB at bf16
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/GLM-OCR-bf16MLX builds
1 on mlx-community| GLM-OCR-bf16 | bf16 | 2.2 GB | 5 GB | 2.6K |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.