Google DeepMind·Gemma

Gemma 3 27B

Added image input, a 128K context window, and support for more than 140 languages.

LegacyLanguageReasoningMultimodalOpen weights

MODEL NUMBER103

Specifications

Only published specifications are shown.

Total parameters

27B

Architecture

Dense

Context

128K

Input modalities

Text · Image

Output modalities

Text

Open weights

Yes

License

Gemma Terms

Status

Legacy

Added image input, a 128K context window, and support for more than 140 languages.

PreviousGemma 2 27B27B · 8K ctx

CurrentGemma 3 27B27B · 128K ctx

New capabilities Vision Multilingual Long context

VisionMultilingualLong context

2025-03-12Open weights

Gemma 3 added vision and 128K context.

Select a card to view the related model.