gemma-4-E2B-it
google/gemma-4-E2B-it
Google · Gemma · Language models · family gemma4
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 |
|---|---|---|---|---|
| gemma4-e2b-it | iOS | none 4bit_palettized.yaml |
float16 | 128K |
| Exported via models/gemma4/export.py (standalone recipe -- doesn't fit coreai.llm.export's single-graph pipeline: a per-context blocked ladder of statically-shaped programs, externalized Per-Layer Embeddings, and precomputed dual-RoPE rows). Pass --include-vision for image input. | ||||
Export it
From a checkout of apple/coreai-models, with uv installed:
uv run coreai.llm.export gemma4-e2b-it --platform iOS
Links
- Apple’s model card and Swift examples
- Original model on Hugging Face
- 10 Apple/MLX builds of this model
First seen in the catalogue 2026-11-11.