Gemma 3n 4B

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements. This model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions. [Read more in the blog post](https://developers.googleblog.com/en/introducing-gemma-3n/)

ChatGoogle33k tokens$0.0654 / $0.1308 · 1M

google/gemma-3n-e4b-it

Context
33k tokens
Completion cap
—
Tools
No
JSON
Yes
Released
2025-05-20

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-3n-e4b-it",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Gemma 3n 4B?
Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements. This model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions. [Read more in the blog post](https://developers.googleblog.com/en/introducing-gemma-3n/) Gemma 3n 4B runs on the Geek Hub API (OpenAI-compatible). Model id: google/gemma-3n-e4b-it.
Is Gemma 3n 4B free?
No. Input is $0.0654 per 1M tokens and output is $0.1308 per 1M tokens on Geek Hub (markup included).
What is the context length of Gemma 3n 4B?
Gemma 3n 4B has a 33k tokens context window.
Does Gemma 3n 4B support tool calling and structured outputs?
Gemma 3n 4B does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was Gemma 3n 4B released?
Gemma 3n 4B was released on 2025-05-20.

More models from Google