8-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/GLM-4.5V-abliterated-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- zai-org/GLM-4.5V (quantized)
- Vendor
- zai-org
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- mit
- Downloads
- 119 in the last 30 days · 1.5K all time · 1 likes
- Published
- 2025-08-24 · updated 2025-09-05 (1y ago)
- Languages
- zh, en
- Tags
- glm4v_moe, abliterated, uncensored
Other MLX builds of zai-org/GLM-4.5V
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Huihui-GLM-4.5V-abliterated-mxfp4 | MXFP4 | ≈ 61.9 GB | 96 GB+ | 259 |
| GLM-4.5V-abliterated-8bit (this one) | 8-bit | — | — | 119 |
| Huihui-GLM-4.5V-abliterated-5bit | 5-bit | — | — | 79 |
| GLM-4.5V-abliterated-4bit | 4-bit | — | — | 77 |