google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 1.32M • 606
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 1.59M • 1.05k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 2.28M • • 1.42k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 68.7k • 158 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 70.7k • • 196 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 3.69M • • 1.06k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 25.5k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.22M • • 789 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 9.69k • 124
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 847k • • 2kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 6.3k • 166Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 2.44k • 271 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 48 • 27 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.08k • 143 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 45 • 15 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.74k • 287 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 90 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 225 • 400
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 1 • 32Note ^ GGUFs to be used in llama.cpp and Ollama. We strongly recommend using the IT models.
-
google/gemma-3-270m-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 67 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 674 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 2.02k • • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 331 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 101k • • 150 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 66 • • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 31 • • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 428 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 144 • • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision