4-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-4.1V-9B-Thinking-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- zai-org/GLM-4-9B-0414 (quantized)
- Vendor
- zai-org
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 84 in the last 30 days · 842 all time · 0 likes
- Published
- 2025-11-10 · updated 2025-11-10 (1y ago)
- Languages
- en, zh
- Tags
- glm4v, reasoning
Other MLX builds of zai-org/GLM-4-9B-0414
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-4-9B-0414-4bit | 4-bit | ≈ 5.3 GB | 8 GB+ | 852 |
| GLM-4-9B-0414-6bit | 6-bit | ≈ 7.6 GB | 16 GB+ | 59 |
| GLM-4-9B-0414-8bit | 8-bit | ≈ 10.0 GB | 16 GB+ | 114 |
| GLM-4-9B-0414-bf16 | bf16 | ≈ 18.8 GB | 24 GB+ | 63 |
| GLM-4.1V-9B-Thinking-4bit (this one) | 4-bit | — | — | 84 |
| GLM-4.1V-9B-Thinking-5bit | 5-bit | — | — | 60 |