google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 91.7k • 624
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 749k • 1.09k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.68M • • 1.48k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 87.5k • 162 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 61.9k • 201 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 2.68M • • 1.15k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 36.2k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 700k • • 823 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 12k • 124
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 354k • • 2.02kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 9.37k • 170Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 2.52k • 283 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 34 • 28 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 830 • 152 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 82 • 16 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 946 • 296 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 26 • 22 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 414 • 401
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 27 • 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 • 150 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 331 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 134 • 12 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 488 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 66.5k • • 179 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 152 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 54 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 36 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 129 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision