Atlas / Models / Google / Google: Gemma 3n 4B

Google: Gemma 3n 4B✓ Catalog verified

google/gemma-3n-e4b-it

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

Input price
$0.02 /1M
Output price
$0.04 /1M
Context
33K
Modalities
text
Released
May 20, 2025
Tool calling
Atlas signal
79/100
01

Overview

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

Access: available through the official Google API. Context window: 33K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifiergoogle/gemma-3n-e4b-it
ProviderGoogle
Model typeText LLM
Context window33K catalog
Input modalitiestext
Output modalitiestext
ReleasedMay 20, 2025
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltystoptemperaturetop_ktop_p
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for google/gemma-3n-e4b-it as published in the catalog.

$0.02
Input /1M
$0.04
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$2e-8$0.02 / 1MPer input token
Completion tokens$4e-8$0.04 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.02Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool CallingNot advertisedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Google: Gemma 3n 4B
MMLU Signal (Reasoning)
74signal
Coding Signal (HumanEval proxy)
84signal
Math Signal (GSM8K proxy)
74signal
Science Signal (GPQA proxy)
82signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Google: Gemma 3n 4B through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="google/gemma-3n-e4b-it",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Google: Gemma 3n 4B cost?

$0.02 per 1M input tokens and $0.04 per 1M output tokens on the official Google API.

What is the context window of Google: Gemma 3n 4B?

Google: Gemma 3n 4B supports up to 33K tokens of context.

Does Google: Gemma 3n 4B support tool / function calling?

Google: Gemma 3n 4B does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.

How do I access Google: Gemma 3n 4B?

Use the official Google API with the model id `google/gemma-3n-e4b-it`. See the Quick start section above for code examples.