Z.ai · First MLX build 24 Aug 2025
GLM-4.5V
MLX
TextVision mit
A 108B parameter vision and text model from Z.ai, with 4 MLX builds, from MXFP4 to 4-bit.
- Parameters
- 108B From Hugging Face
- Quantisation
- MXFP4 Huihui-GLM-4.5V-abliterated-mxfp4
- Memory needed
- 72 GB Estimate, unified memory
- Download
- 61.9 GB Weights, estimated
- Downloads
- 263 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 72 GB at MXFP4
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 · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Huihui-GLM-4.5V-abliterated-mxfp4 --image photo.jpg --prompt "Describe this image"MLX builds
4 on mlx-community| Huihui-GLM-4.5V-abliterated-mxfp4 | MXFP4 | 61.9 GB | 72 GB | 263 |
|---|---|---|---|---|
| GLM-4.5V-abliterated-8bit | 8-bit | — | — | 120 |
| Huihui-GLM-4.5V-abliterated-5bit | 5-bit | — | — | 81 |
| GLM-4.5V-abliterated-4bit | 4-bit | — | — | 76 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.