---
license: gemma
base_model: google/gemma-4-E2B-it
library_name: basert
pipeline_tag: text-generation
tags:
  - basert
  - apple-silicon
  - quantized
---

# gemma-4-E2B-it

[BaseRT](https://github.com/basecompute/baseRT) `.base` builds of [`google/gemma-4-E2B-it`](https://huggingface.co/google/gemma-4-E2B-it) for fast local inference on Apple Silicon (Metal).

## Files

| File | Precision | Size |
|------|-----------|------|
| `gemma-4-E2B-it-Q4.base` | 4-bit | 2.9 GB |
| `gemma-4-E2B-it-Q8.base` | 8-bit | 5.3 GB |

## Usage

```bash
curl -LsSf https://basecompute.co/install.sh | sh
basert pull basecompute/gemma-4-E2B-it
basert chat basecompute/gemma-4-E2B-it
```

Released under the gemma license, inherited from the base model.