Gemma models
Browse all models from this model family.
-
TranslateGemma is Google’s open Gemma-based translation model family for text and image-text translation across 55 languages.TextReleased 4mo ago
-
MedGemma 1.5 is Google’s open medical image-text model for medical text, radiology, pathology, dermatology, and healthcare AI development.TextReleased 4mo ago
-
Gemma Scope 2 is not a generation model, it is Google’s open interpretability suite for analyzing Gemma 3 model behavior.TextReleased 5mo ago
-
T5Gemma 2 is Google’s encoder-decoder Gemma model collection for input-heavy tasks such as summarization, translation, and deep text understanding.TextReleased 5mo ago
-
Gemma 3 is Google’s open-weight Gemma generation focused on efficient text and multimodal deployment across small and larger hardware targets.TextReleased 1y ago
-
PaliGemma 2 is Google’s upgraded open vision-language model family based on Gemma 2, available in 3B, 10B, and 28B sizes.TextReleased 1y ago
-
TextReleased 1y ago
-
PaliGemma is Google’s open vision-language model that accepts images plus text and outputs text for captioning, visual question answering, OCR-style tasks, and detection.TextReleased 2y ago
-
CodeGemma is Google’s open-weight Gemma coding model family for code completion, code generation, instruction following, and reasoning.TextReleased 2y ago
-
Gemma 1 is Google’s first open-weight lightweight text model family built from the same research and technology as Gemini.TextReleased 2y ago
