4-bit Open on Hugging Face
Parameters
9.4B
Weights (est.)
≈ 5.3 GB
Mac memory (est.)
8 GB+
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-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/GLM-Z1-9B-0414-abliterated-4bit --prompt "Hello"
Details
- Base model
- huihui-ai/GLM-Z1-9B-0414-abliterated
- Vendor
- huihui-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 89 in the last 30 days · 860 all time · 0 likes
- Published
- 2025-04-26 · updated 2025-04-26 (1y ago)
- Languages
- zh, en
- Tags
- glm4, abliterated, uncensored
Other MLX builds of huihui-ai/GLM-Z1-9B-0414-abliterated
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-Z1-9B-0414-abliterated-4bit (this one) | 4-bit | ≈ 5.3 GB | 8 GB+ | 89 |
| GLM-Z1-9B-0414-abliterated-6bit | 6-bit | ≈ 7.6 GB | 16 GB+ | 64 |