google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 1.09M • 601
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 4.12M • 1.04k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.98M • • 1.39k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 48.1k • 156 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 72.2k • • 195 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 4.01M • • 1.04k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 21.2k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.31M • • 774 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 12.3k • 124
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 870k • • 1.99kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 4.4k • 165Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 4.78k • 270 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 47 • 27 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 980 • 136 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 25 • 15 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 2.37k • 286 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 166 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 274 • 401
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 20 • 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 • 93 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 608 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 1.67k • • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 220 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 81.8k • • 132 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 48 • 11 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 36 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 863 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 86 • • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision