Gemma 3n E4B Instruct

Last updated: Recently

Model Type

Text

Max Context

Max Output

Parameter Scale

Gemma 3n E4B Instruct by Google: Text model; TTFT 0.480s, 17.8 tok/s.

Input Modality

Output Modality

Inference Speed

17.805 tokens/s

Latest Release Date

6/26/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Gemma 3n E4B Instruct

Release date

6/26/2025

Performance

17.805 tokens/s

model_creator.name

Google

AA Evaluation Scores

AA Intelligence Index

6.4

AA Coding Index

4.2

AA Math Index

14.3

MMLU Pro

0.488

GPQA

0.296

HLE

0.044

LiveCodeBench

0.146

SciCode

0.081

Math-500

0.771

AIME

0.137

AIME 2025

0.143

IFBench

0.279

LCR

TerminalBench Hard

0.023

TAU2

0.05

Output Speed (tokens/s)

17.805 tok/s

TTFT (s)

0.48s

First Answer Token (s)

0.48s

Google

◎

Gemma 3n E4B Instruct

$0.02/M$0.04/M

Gemma 3n E4B Instruct by Google: Text model; TTFT 0.480s, 17.8 tok/s.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0