google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 56.9k • 712
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 91.1k • 1.15k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.01M • • 1.64k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 290k • • 179 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 39.9k • • 224 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 212k • • 1.31k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 53.8k • • 97 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 366k • • 908 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 9.61k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 357k • • 2.07kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 10.6k • 190Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 6.35k • 335 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 30 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.29k • 183 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 57 • 17 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.48k • 304 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 51 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 420 • 408
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 34 • 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 • 36 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 86 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 85 • 13 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 53 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 7.58k • • 220 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 838 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 42 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 56 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 101 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision