bf16 Open on Hugging Face
Parameters
7.9B
Weights (est.)
≈ 15.9 GB
Mac memory (est.)
24 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-4-e4b-it-bf16 --image photo.jpg --prompt "Describe this image"
Details
- Base model
- google/gemma-4-E4B-it (finetune)
- Vendor
- Google · Gemma
- Task
- Vision + text
- Quantisation
- bf16
- Licence
- gemma
- Downloads
- 609 in the last 30 days · 12K all time · 8 likes
- Published
- 2026-04-02 · updated 2026-07-06 (4mo ago)
- Tags
- gemma4, mlx-vlm
Other MLX builds of google/gemma-4-E4B-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-4-e4b-it-4bit | 4-bit | ≈ 5.1 GB | 8 GB+ | 26K |
| gemma-4-e4b-it-mxfp4 | MXFP4 | ≈ 5.1 GB | 8 GB+ | 268 |
| gemma-4-e4b-it-nvfp4 | 4-bit | ≈ 5.1 GB | 8 GB+ | 239 |
| gemma-4-e4b-it-OptiQ-4bit | 4-bit | ≈ 5.2 GB | 8 GB+ | 1.1K |
| gemma-4-e4b-it-5bit | 5-bit | ≈ 6.1 GB | 16 GB+ | 94 |
| gemma-4-e4b-it-6bit | 6-bit | ≈ 7.0 GB | 16 GB+ | 519 |
| gemma-4-e4b-it-8bit | 8-bit | ≈ 8.9 GB | 16 GB+ | 1.9K |
| gemma-4-e4b-it-mxfp8 | MXFP8 | ≈ 8.9 GB | 16 GB+ | 240 |
| gemma-4-e4b-it-bf16 (this one) | bf16 | ≈ 15.9 GB | 24 GB+ | 609 |