modelgrep
G

Google: Gemma 3n 4B

google/gemma-3n-e4b-it

Cheaper than 92% of paid
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
35
220th fastest
Latency
268ms
first token
Input price
$0.060
25th cheapest
Context
33K

How it compares

Faster than25%
of all ranked models
Cheaper than92%
of all ranked models

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis
GPQA Diamond
28%
Humanity's Last Exam
5%
SciCode
9%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Together$0.060$0.120100%

Specifications

Context window33K
Max output
Knowledge cutoffAug 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Gemma 3n 4B FAQ

How much does Gemma 3n 4B cost?

Gemma 3n 4B costs $0.060 per million input tokens and $0.120 per million output tokens via OpenRouter, making it 25th cheapest of 298 paid models.

How fast is Gemma 3n 4B?

Gemma 3n 4B generates around 35 tokens per second with 268ms time-to-first-token (p50), the 220th fastest tracked model.

What is Gemma 3n 4B's context window?

Gemma 3n 4B supports a 33K-token context window. It accepts text input.

Compare head-to-head