5-bit Open on Hugging Face
Parameters
353B
Weights (est.)
≈ 243 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-4.6-5bit --prompt "Hello"
Details
- Base model
- zai-org/GLM-4.6 (quantized)
- Vendor
- zai-org
- Task
- Text generation
- Quantisation
- 5-bit
- Licence
- mit
- Downloads
- 104 in the last 30 days · 4.0K all time · 3 likes
- Published
- 2025-09-30 · updated 2025-09-30 (1y ago)
- Languages
- en, zh
- Tags
- glm4_moe
Other MLX builds of zai-org/GLM-4.6
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-4.6-4bit | 4-bit | ≈ 199 GB | 256 GB+ | 287 |
| GLM-4.6-5bit (this one) | 5-bit | ≈ 243 GB | 512 GB+ | 104 |
| GLM-4.6-bf16 | bf16 | ≈ 706 GB | > 512 GB | 45 |