8-bit Open on Hugging Face
Parameters
353B
Weights (est.)
≈ 375 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-4.6-8bit --prompt "Hello"
Details
- Base model
- mlx-community/GLM-4.6-bf16 (quantized)
- Vendor
- —
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- mit
- Downloads
- 34 in the last 30 days · 762 all time · 2 likes
- Published
- 2025-11-23 · updated 2025-11-23 (11mo ago)
- Languages
- en, zh
- Tags
- glm4_moe
Other MLX builds of mlx-community/GLM-4.6-bf16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-4.6-6bit | 6-bit | ≈ 287 GB | 512 GB+ | 27 |
| GLM-4.6-8bit (this one) | 8-bit | ≈ 375 GB | 512 GB+ | 34 |