4-bit Open on Hugging Face
Parameters
348B
Weights (est.)
≈ 206 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-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/GLM-5.3-Flash-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- zai-org/GLM-5.3-Flash (quantized) · GLM 5.3 Flash on the radar →
- Vendor
- zai-org
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 3.2K in the last 30 days · 5.1K all time · 8 likes
- Published
- 2026-09-25 · updated 2026-09-25 (1mo ago)
- Tags
- glm5_next