MXFP4 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-5.2-mxfp4 --prompt "Hello"
Details
- Base model
- zai-org/GLM-5.2-FP8 (quantized)
- Vendor
- zai-org
- Task
- Text generation
- Quantisation
- MXFP4
- Licence
- —
- Downloads
- 4.4K in the last 30 days · 102K all time · 21 likes
- Published
- 2026-06-16 · updated 2026-06-18 (4mo ago)
- Languages
- en
- Tags
- glm_moe_dsa