4-bit Open on Hugging Face
Parameters
353B
Weights (est.)
≈ 199 GB
Mac memory (est.)
256 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-4.7-4bit --prompt "Hello"
Details
- Base model
- zai-org/GLM-4.7 (quantized)
- Vendor
- zai-org
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 629 in the last 30 days · 96K all time · 5 likes
- Published
- 2025-12-22 · updated 2026-01-01 (10mo ago)
- Languages
- en, zh
- Tags
- glm4_moe
Other MLX builds of zai-org/GLM-4.7
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-4.7-4bit (this one) | 4-bit | ≈ 199 GB | 256 GB+ | 629 |
| GLM-4.7-6bit | 6-bit | ≈ 287 GB | 512 GB+ | 203 |
| GLM-4.7-8bit | 8-bit | ≈ 375 GB | 512 GB+ | 118 |