8-bit Open on Hugging Face
Parameters
12B
Weights (est.)
≈ 12.5 GB
Mac memory (est.)
16 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/Gemma-3-Glitter-12B-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- allura-org/Gemma-3-Glitter-12B (quantized)
- Vendor
- allura-org
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- —
- Downloads
- 22 in the last 30 days · 454 all time · 0 likes
- Published
- 2025-09-29 · updated 2025-09-29 (1y ago)
- Tags
- gemma3, mergekit, merge, mlx-my-repo