google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 68.6k • 610
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 1.33M • 1.07k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.24M • • 1.46k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 70.7k • 159 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 63.1k • • 197 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 5.06M • • 1.1k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 32.8k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.2M • • 810 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 10.1k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 627k • • 2.01kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 7.89k • 167Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 3.62k • 278 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 23 • 27 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 828 • 146 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 62 • 15 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.16k • 291 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 19 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 425 • 400
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 9 • 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 • 180 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 375 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 285 • • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 124 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 90.7k • • 163 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 128 • • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 180 • • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 144 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 107 • • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision