GoogleReleased on Jun 26, 2025

Gemma 3n E4B: Benchmarks, Pricing & Context Window

Gemma 3n E4B is a language model from Google, released in June 2025, with multimodal input.

Gemma 3n is a multimodal model designed to run locally on hardware, supporting image, text, audio, and video inputs. It features a language decoder, audio encoder, and vision encoder, and is available in two sizes: E2B and E4B. The model

Gemma 3n E4B API

API access coming soon

Gemma 3n E4B will be available through our gateway shortly.

Gemma 3n E4B examples

Recent arena outputs from Gemma 3n E4B, picked from the highest-ranked matchups.

Gemma 3n E4B license

Gemma 3n E4B is released under the Proprietary license, which restricts commercial use, has 8.0B parameters, has a knowledge cutoff of June 2024.

License
Proprietary
Non-commercial
Parameters
8.0B
Knowledge cutoff
June 2024

Proprietary license - usage restrictions apply

FAQ

Common questions about Gemma 3n E4B.

What is the Gemma 3n E4B release date?

Gemma 3n E4B was released on June 26, 2025 by Google.

Who created Gemma 3n E4B?

Gemma 3n E4B was created by Google.

How many parameters does Gemma 3n E4B have?

Gemma 3n E4B has 8.0 billion parameters.

What is the license for Gemma 3n E4B?

Gemma 3n E4B is released under the Proprietary license.

What is the knowledge cutoff date for Gemma 3n E4B?

Gemma 3n E4B has a knowledge cutoff of June 2024. This means the model was trained on data up to this date and may not have information about events after this time.

Is Gemma 3n E4B multimodal?

Yes, Gemma 3n E4B is a multimodal model that can process both text and images as input.