4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
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-3-27b-it-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- google/gemma-3-27b-pt (finetune)
- Vendor
- Google · Gemma
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 1.1K in the last 30 days · 34K all time · 13 likes
- Published
- 2025-03-12 · updated 2025-03-19 (1y ago)
- Tags
- gemma3
Other MLX builds of google/gemma-3-27b-pt
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-3-27b-it-4bit (this one) | 4-bit | — | — | 1.1K |
| medgemma-27b-it-8bit | 8-bit | — | — | 301 |
| medgemma-27b-it-4bit | 4-bit | — | — | 155 |
| gemma-3-27b-it-8bit | 8-bit | — | — | 110 |
| medgemma-27b-it-bf16 | bf16 | — | — | 76 |
| gemma-3-27b-it-bf16 | bf16 | — | — | 66 |
| medgemma-27b-it-6bit | 6-bit | — | — | 57 |
| gemma-3-27b-it-6bit | 6-bit | — | — | 45 |