gemma3n:e4b

Family context: Gemma 3n family

Publisher: Google DeepMind

Google describes Gemma 3n as a multimodal family designed for devices with limited resources. Selective parameter activation gives different effective and total parameter counts.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published family information

Documented effective sizes

2B and 4B Source

Documented input types

Text, images, video and audio Source

Output

Text Source

Published input context

32K tokens Source

Publisher-described uses

• Device-oriented multimodal understanding and text generation. Source

Reference limitations

• Effective parameter size is not the total stored parameter count. A runtime may expose only a subset of the upstream input types. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Gemma 3n family official documentation — Google DeepMind. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Google AI / Google DeepMind — official site
• Ollama
• Provider page
• Hugging Face
• Official model announcement / documentation

Where gemma3n:e4b comes from

Named in 1 observation page

• 3B-7B local models — all 53 · V1