google/gemma-3-270m-it
Text Generation • Updated • 159k • 584
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 3.14M • 1.02k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 2.06M • • 1.33k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 427k • 154 -
google/gemma-3-1b-pt
Text Generation • Updated • 140k • • 194 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 1,000k • • 954 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 18.5k • 90 -
google/gemma-3-12b-it
Image-Text-to-Text • Updated • 2.83M • • 719 -
google/gemma-3-27b-pt
Image-Text-to-Text • Updated • 8.45k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 993k • • 1.97kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 4.16k • 162Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 9.59k • 259 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 49 • 26 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 763 • 127 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 39 • 14 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 4.45k • 271 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 70 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 588 • 399
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 5 • 31Note ^ 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 • 116 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 97 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 167 • • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 123k • • 41 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 61.3k • • 105 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 68 • • 11 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 807 • • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 66 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 30 • • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision