# Gemma 3n E2B Instructed

Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based on the MatFormer architecture, it supports nested submodels and modular composition via the Mix-and-Match framework. Gemma 3n models are optimized for low-resource deployment, offering 32K context length and strong multilingual and reasoning performance across common benchmarks. This variant is trained on a diverse corpus including code, math, web, and multimodal data.

## Model Information

- **Organization**: [google](/llm.txt)
- **Slug**: gemma-3n-e2b-it
- **Available at Providers**: 8
- **Release Date**: June 26, 2025

### Benchmark Scores
- AIME 2025: 0.067
- GPQA: 0.248

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [Nvidia](/llm/nvidia.txt) | gemma-3n-e2b-it | 0.00 | 0.00 | Yes | [View](https://build.nvidia.com/google/gemma-3n-e2b-it) |
| [ValorGPT](/llm/valorgpt.txt) | Gemma 3n 2B |  |  | Yes | [View](https://www.valorgpt.com/models/google-gemma-3n-e2b-it-free) |
| [Routeway](/llm/routeway.txt) | Google: Gemma 3n 2B | 0.03 | 0.02 |  | [View](https://routeway.ai/models) |
| [Kilo Code](/llm/kilocode.txt) | Google: Gemma 3n 2B (free) | 0.00 | 0.00 | Yes |  |
| [Chats-LLM](/llm/chatsllm.txt) | Google: Gemma 3n 2B | 0.00 | 0.00 | Yes |  |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/google/gemma-3n-e2b-it:free |  |  |  |  |
| [OpenRouter](/llm/openrouter.txt) | Gemma 3n 2B (free) | 0.00 | 0.00 | Yes | [View](https://openrouter.ai/google/gemma-3n-e2b-it:free) |
| [Writingmate](/llm/writingmate.txt) | Google: Gemma 3n 2B (free) |  |  |  | [View](https://writingmate.ai/models/google/gemma-3n-e2b-it) |

---

[← Back to all providers](/llm.txt)