Skip to main content
Language model

Gemma 3n E2B IT

Google

Released
June 26, 2025
Data date
October 28, 2026
Benchmark-Meta-Score
Unavailable
No independent results
Input
Text, Image, Audio
Output
Text

Gemma 3n E2B IT accepts text, images, and audio and responds with text. E2B identifies the model variant; the recorded catalog lists 6 billion total parameters. Its context window holds 32,768 tokens.

Specifications and access

SpecificationValue and source
Weights
Open weightsSource
Parameters
6 billionSource
Context window
32,768 tokensSource
Maximum output
32,768 tokensSource
Knowledge Cutoff
June 2024Source
License
Gemma Terms of UseSource
Inputs
Text, Image, AudioSource
Outputs
TextSource
Tool calling
Effective model size
2 B (Effective model size reported by Google. This is not an active MoE parameter count per token.)Source