8-bit Open on Hugging Face
Parameters
5.0B
Weights (est.)
≈ 5.7 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-3-4b-it-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- google/gemma-3-4b-pt (finetune)
- Vendor
- Google · Gemma
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- gemma
- Downloads
- 18K in the last 30 days · 159K all time · 6 likes
- Published
- 2025-03-12 · updated 2025-03-19 (1y ago)
- Tags
- gemma3
Other MLX builds of google/gemma-3-4b-pt
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-3-4b-it-4bit | 4-bit | ≈ 3.4 GB | 8 GB+ | 2.7K |
| gemma-3-4b-it-6bit | 6-bit | ≈ 4.5 GB | 8 GB+ | 47 |
| gemma-3-4b-it-8bit (this one) | 8-bit | ≈ 5.7 GB | 16 GB+ | 18K |
| gemma-3-4b-it-bf16 | bf16 | ≈ 9.9 GB | 16 GB+ | 640 |