gemma-3n-E4B
A 7.8B parameter vision and text model from Google, with 6 MLX builds, from 3-bit to 6-bit and Apple Core AI export recipes for macOS.
- Parameters
- 7.8B From Hugging Face
- Quantisation
- 4-bit gemma-3n-E4B-it-4bit
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 424 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 6 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 7.8B From Hugging Face
- Compression
- 4-bit Apple’s preset
- Memory needed
- 7 GB Estimate from parameters
- Context
- 32K tokens Fixed at export
- Precision
- FP16 Compute precision
- Platforms
- macOS Mac
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 3 Sept 2026 First registry commit
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/gemma-3n-E4B-it-4bit --image photo.jpg --prompt "Describe this image"Memory
Estimated from the parameter count at Apple’s compression setting. Apple does not publish package sizes.
Export it
Terminal · uv$ git clone https://github.com/apple/coreai-models
$ cd coreai-models
$ uv run coreai.llm.export gemma-3n-e4b
Apple publishes the recipe, not a ready-made package: these commands convert the original weights to a Core AI .aimodel on your Mac. See the repository for requirements.
MLX builds
6 on mlx-community| gemma-3n-E4B-it-3bit | 3-bit | 5.0 GB | 8 GB | 27 |
|---|---|---|---|---|
| gemma-3n-E4B-it-bf16 | bf16 | 15.7 GB | 20 GB | 159 |
| gemma-3n-E4B-it-4bit | 4-bit | — | — | 424 |
| gemma-3n-E4B-it-5bit | 5-bit | — | — | 56 |
| gemma-3n-E4B-it-8bit | 8-bit | — | — | 51 |
| gemma-3n-E4B-it-6bit | 6-bit | — | — | 32 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.
Core AI export presets
From Apple’s registry| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| gemma-3n-e4b | macOS | 4-bit | FP16 | 32K |