Gemma 3 4B is cataloged under Google / Gemma with canonical ID google/gemma-3-4b-it.

GOGoogle/ Gemma

Gemma 3 4B

google/gemma-3-4b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Compare

Model information

Released

2025-03-13

Context window

131K

Max output

16K

Model parameters

4.3B

Weights

Open

Modalities

Input

ImageText

Output

Text

Identity

Version: gemma-3-4b-it
Knowledge cutoff: 2024-08-31

Resources

Hugging Face

Capabilities

Open weightStructuredTemperature

Providers

Provider	Provider model ID	Protocol	Context	Max output	Capabilities	Notes	Pricing	Streaming
OpenRouter	google/gemma-3-4b-it	openai_chat	131K	16K	AttachmentsStructuredTemperature	Hugging Face: google/gemma-3-4b-it	input $0.05/M · output $0.1/M	Yes
Nvidia	google/gemma-3-4b-it	openai_chat	131K	16K	AttachmentsTool callTemperature	-	input $0/M · output $0/M	Yes
Kilo Gateway	google/gemma-3-4b-it	openai_chat	131K	16K	AttachmentsStructuredTemperature	-	input $0.05/M · output $0.1/M	Yes
Google	gemma-3-4b-it	custom	131K	16K	-	-	-	Yes

Model information

Modalities

Identity

Resources

Capabilities

Providers

FAQ

What is Gemma 3 4B?

Where can I access Gemma 3 4B?

What are the context and output limits?

What can Gemma 3 4B handle?