Gemma 3n 4B

Open weight

Google · Released May 2025 · Knowledge cutoff August 2024

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...

It is part of Google's Gemini and Gemma catalog: Pro tiers lead on capability, Flash tiers on speed and price, and Gemma models are open weight.

Facts and pricing

Provider
Google
Context window
33K tokens
Input price
0.66 credits / 1M tokens ($0.060 raw)
Output price
1.3 credits / 1M tokens ($0.12 raw)
Vision (image input)
No
Tool calling
No
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Gemma 3n 4B now

Ask Gemma 3n 4B anything. Your prompt opens in the Zeplik app with this model selected.

Gemma 3n 4B

What Gemma 3n 4B is best for

Example prompts

Prompts that suit a open weight model like Gemma 3n 4B:

Google family

ModelContextInput cr/MOutput cr/MReleased
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)66K2.816.5June 2026
Nano Banana 2 (Gemini 3.1 Flash Image)131K5.533.0June 2026
Nano Banana Pro (Gemini 3 Pro Image)66K22.0132June 2026
Gemini 3.5 Flash1.0M16.599.0May 2026
Gemini 3.1 Flash Lite1.0M2.816.5May 2026
Gemma 4 26B A4B (free)262K00April 2026
Gemma 4 26B A4B262K0.663.6April 2026
Gemma 4 31B (free)262K00April 2026
Gemma 4 31B262K1.33.8April 2026
Lyria 3 Pro Preview1.0M00March 2026

All 28 Google models

Frequently asked questions

What is Gemma 3n 4B?
Gemma 3n 4B is an AI model by Google. 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...
How much does Gemma 3n 4B cost on Zeplik?
Input tokens cost 0.66 credits per million and output tokens 1.3 credits per million (1 credit = $0.10; the raw provider rates are $0.060 and $0.12 per million). New accounts start with free credits.
How long can a conversation with Gemma 3n 4B be?
Gemma 3n 4B has a 33K-token context window (32,768 tokens), which covers the conversation plus any documents you attach.
Does Gemma 3n 4B support images and tools?
Gemma 3n 4B is text-only and does not support tool calling.

Related models

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Fast and light

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

66K ctx16.5 cr/M outJune 2026
Nano Banana 2 (Gemini 3.1 Flash Image)Fast and light

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

131K ctx33.0 cr/M outJune 2026
Nano Banana Pro (Gemini 3 Pro Image)Fast and light

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

66K ctx132 cr/M outJune 2026
Gemini 3.5 FlashFast and light

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

1.0M ctx99.0 cr/M outMay 2026
Gemini 3.1 Flash LiteFast and light

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...

1.0M ctx16.5 cr/M outMay 2026
Gemma 4 26B A4B (free)Open weight

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

262K ctx0 cr/M outApril 2026
Gemma 3n 4B - Google AI Model | Zeplik Chat