MXFP4 Open on Hugging Face
Parameters
744B
Weights (est.)
≈ 419 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-MXFP4-Q8 --prompt "Hello"
Details
- Base model
- zai-org/GLM-5 (quantized)
- Vendor
- zai-org
- Task
- Text generation
- Quantisation
- MXFP4
- Licence
- mit
- Downloads
- 106 in the last 30 days · 12K all time · 1 likes
- Published
- 2026-02-12 · updated 2026-02-13 (9mo ago)
- Languages
- en, zh
- Tags
- glm_moe_dsa, mxfp4, quantized
Other MLX builds of zai-org/GLM-5
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| GLM-5-4bit | 4-bit | ≈ 419 GB | 512 GB+ | 224 |
| GLM-5-MXFP4-Q8 (this one) | MXFP4 | ≈ 419 GB | 512 GB+ | 106 |
| GLM-5 | — | ≈ 1488 GB | > 512 GB | 119 |