# Google: Gemma 3n 2B: AI model fact sheet

- **Provider:** google
- **Released:** 2025-07-09
- **Context window:** 8,192 tokens
- **API pricing:** $0.000 / 1M input, $0.000 / 1M output
- **OpenRouter ID:** google/gemma-3n-e2b-it:free
- **Capabilities:** conversation, reasoning, translation

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.

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/gemma-3n-e2b-it-free