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-5.3-4bit --prompt "Hello"
Details
- Base model
- zai-org/GLM-5.3-BF16 (quantized)
- Vendor
- zai-org
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- glm-5.3
- Downloads
- 2.1K in the last 30 days · 4.5K all time · 4 likes
- Published
- 2026-09-02 · updated 2026-09-02 (2mo ago)
- Languages
- en, zh
- Tags
- glm_moe_dsa
Other MLX builds of zai-org/GLM-5.3-BF16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-5.3-4bit (this one) | 4-bit | ≈ 418 GB | 512 GB+ | 2.1K |
| GLM-5.3-mixed-4_5bit | 5-bit | ≈ 511 GB | > 512 GB | 434 |