4-bit Open on Hugging Face
Parameters
743B
Weights (est.)
≈ 418 GB
Mac memory (est.)
512 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-5.2-4bit --prompt "Hello"
Details
- Base model
- zai-org/GLM-5.2 (quantized) · GLM 5.2 on the radar →
- Vendor
- zai-org
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 527 in the last 30 days · 19K all time · 6 likes
- Published
- 2026-06-20 · updated 2026-07-12 (4mo ago)
- Tags
- glm_moe_dsa
Other MLX builds of zai-org/GLM-5.2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-5.2-4bit (this one) | 4-bit | ≈ 418 GB | 512 GB+ | 527 |
| GLM-5.2-DQ4plus-q8 | 8-bit | ≈ 790 GB | > 512 GB | 724 |