4-bit Open on Hugging Face
Parameters
33B
Weights (est.)
≈ 18.3 GB
Mac memory (est.)
24 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-4-32B-0414-4bit --prompt "Hello"
Details
- Base model
- THUDM/GLM-4-32B-0414
- Vendor
- THUDM
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 152 in the last 30 days · 8.9K all time · 4 likes
- Published
- 2025-04-21 · updated 2025-04-21 (1y ago)
- Languages
- zh, en
- Tags
- glm4
Other MLX builds of THUDM/GLM-4-32B-0414
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-4-32B-0414-4bit (this one) | 4-bit | ≈ 18.3 GB | 24 GB+ | 152 |
| GLM-4-32B-0414-4bit-DWQ | 4-bit DWQ | ≈ 18.3 GB | 24 GB+ | 50 |
| GLM-4-32B-0414-8bit | 8-bit | ≈ 34.6 GB | 48 GB+ | 80 |