Skip to content

GLM-5.2-fp8

mlx-community/GLM-5.2-fp8
8-bit Open on Hugging Face
Parameters
743B
Weights (est.)
≈ 790 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-fp8 --prompt "Hello"

Details

Base model
—
Vendor
—
Task
Text generation
Quantisation
8-bit
Licence
—
Downloads
175 in the last 30 days · 27K all time · 0 likes
Published
2026-06-22 · updated 2026-06-22 (4mo ago)
Languages
en
Tags
glm_moe_dsa