google/gemma-3-270m-it
Text Generation • Updated • 102k • 567
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 89k • 1k -
google/gemma-3-4b-it
Image-Text-to-Text • Updated • 1.73M • 1.26k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 155k • 150 -
google/gemma-3-1b-pt
Text Generation • Updated • 61.7k • 187 -
google/gemma-3-1b-it
Text Generation • Updated • 1.89M • 894 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 30.4k • 88 -
google/gemma-3-12b-it
Image-Text-to-Text • Updated • 2.49M • • 696 -
google/gemma-3-27b-pt
Image-Text-to-Text • Updated • 15.8k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 1.1M • • 1.94kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 5.18k • 155Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 15.4k • 249 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 118 • 24 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.52k • 121 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 46 • 12 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 8.73k • 260 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 124 • 19 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 7.44k • 398
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 97 • 30Note ^ 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 • 45 • 8 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 208 • 12 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 456 • 10 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 10.6k • 39 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 27.5k • • 80 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 298 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 205 • 9 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 795 • 11
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 599 • 13Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision