Language model

Gemma 4 E4B IT

Google

Released: April 2, 2026
Data date: September 26, 2026

Google Gemma 4 E4B IT is distinguished by the middle E variant with roughly 4.5 billion effective parameters and 8 billion including embeddings. It sits above Gemma 4 E2B IT without reaching the size of the 12B or 31B variants.

Google documents a 131,072-token context with text, image, and audio input, and the weights use Apache 2.0.

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	APISource
Parameters	8 billionSource
Context window	131,072 tokensSource
Maximum output	8,192 tokensSource
License	Apache 2.0Source
Inputs	Text, Image, AudioSource
Outputs	TextSource
Reasoning	YesSource
Tool calling	YesSource

Sources and data date

Type	Evidence and data date
Additional source	models.dev catalog (retrieved September 26, 2026) · models.dev model catalog · Editorial description reviewed October 2, 2026
Additional source	Hugging Face · Gemma 4 E4B instruction-tuned weights · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0

Specifications and access

Popularity

Sources and data date