# Gemma 4 E4B

> Canonical: https://www.overmindlab.ai/models/gemma-4-e4b-it

Default small Gemma 4 — stronger than E2B for laptop multimodal use.

| Property | Value |
| --- | --- |
| Model ID | google/gemma-4-E4B-it |
| Provider | Google |
| Group | Gemma 4 |
| Parameters | E4B (~8B) |
| Tier | Small |
| Context window | 128K |
| Max training context | 128K |
| Tool calling | Yes |
| Training methods | — |
| Training cost | from $0.75 |
| Serving cost (per 1M output tokens) | from $4.00 |

## Overview

Gemma 4 E4B is the recommended small instruct tier for local multimodal work. Same 128K context and thinking controls as E2B with more capacity for coding and tool use.

Google DeepMind Gemma 4 open models: hybrid thinking, 140+ languages, dense and MoE sizes from edge to server.

## Good for

- Laptop multimodal + tool agents
- Coding LoRA when E2B underfits
- Speech/text fine-tunes on a single GPU

Train this model on your agent's data: https://docs.overmindlab.ai/models/training.md

## Related models

- [Gemma 4 E2B](https://www.overmindlab.ai/models/gemma-4-e2b-it): E2B (~5.1B), 128K context
- [Gemma 4 12B](https://www.overmindlab.ai/models/gemma-4-12b-it): 12B, 256K context
- [Gemma 4 31B](https://www.overmindlab.ai/models/gemma-4-31b-it): 31B, 256K context
- [Gemma 4 26B-A4B](https://www.overmindlab.ai/models/gemma-4-26b-a4b-it): 26B (4B active), 256K context