google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 143k • 609
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 1.73M • 1.07k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.33M • • 1.45k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 73.3k • 159 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 65.3k • 196 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 5.12M • • 1.09k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 33.1k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.23M • • 806 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 9.61k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 768k • • 2.01kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 8.15k • 166Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 3.6k • 278 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 19 • 27 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 972 • 146 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 47 • 15 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.15k • 291 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 21 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 375 • 400
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 2 • 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 • 152 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 362 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 539 • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 152 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 83.8k • • 160 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 120 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 184 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 188 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 122 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision