gemma-3n-E4B
google/gemma-3n-E4B
Google · Gemma · Language models · family gemma3n
macOS
Apple’s model card
Apple lists this model in its Core AI model registry, which means there is a supported recipe for converting it to the .aimodel format. The converted model is not hosted by Apple; you run the export yourself with the command below.
Export presets
| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| gemma-3n-e4b | macOS | 4bit gemma3n_e2b_4bit_embedding_excluded.yaml |
float16 | 32K |
Export it
From a checkout of apple/coreai-models, with uv installed:
uv run coreai.llm.export gemma-3n-e4b
Links
- Apple’s model card and Swift examples
- Original model on Hugging Face
- 12 Apple/MLX builds of this model
First seen in the catalogue 2026-11-11.