google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 344k • 609
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 2.2M • 1.06k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.71M • • 1.44k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 74.1k • 159 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 63k • 196 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 4.97M • • 1.08k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 38.6k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.28M • • 797 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 9.49k • 124
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 820k • • 2.01kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 8.22k • 166Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 3.33k • 276 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 41 • 27 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.12k • 146 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 36 • 15 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.32k • 291 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 20 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 277 • 399
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 • 162 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 325 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 1.35k • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 211 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 87.3k • • 157 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 112 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 37 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 285 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 114 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision