4-bit Open on Hugging Face
Parameters
5.1B
Weights (est.)
≈ 3.6 GB
Mac memory (est.)
8 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-e2b-it-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- google/gemma-4-E2B-it (quantized)
- Vendor
- Google · Gemma
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 25K in the last 30 days · 627K all time · 38 likes
- Published
- 2026-04-02 · updated 2026-07-06 (4mo ago)
- Tags
- gemma4, mlx-vlm
Other MLX builds of google/gemma-4-E2B-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-4-e2b-it-OptiQ-4bit | 4-bit | ≈ 2.6 GB | 8 GB+ | 533 |
| Gemma4-E2B-IT-Text-int4 | — | ≈ 2.6 GB | 8 GB+ | 491 |
| gemma-4-e2b-it-4bit (this one) | 4-bit | ≈ 3.6 GB | 8 GB+ | 25K |
| gemma-4-e2b-it-mxfp4 | MXFP4 | ≈ 3.6 GB | 8 GB+ | 211 |
| gemma-4-e2b-it-nvfp4 | 4-bit | ≈ 3.6 GB | 8 GB+ | 140 |
| gemma-4-e2b-it-5bit | 5-bit | ≈ 4.1 GB | 8 GB+ | 158 |
| gemma-4-e2b-it-6bit | 6-bit | ≈ 4.7 GB | 8 GB+ | 298 |
| gemma-4-e2b-it-8bit | 8-bit | ≈ 5.9 GB | 16 GB+ | 767 |
| gemma-4-e2b-it-mxfp8 | MXFP8 | ≈ 5.9 GB | 16 GB+ | 144 |
| gemma-4-e2b-it-bf16 | bf16 | ≈ 10.2 GB | 16 GB+ | 1.5K |