google/gemma-3-270m-it
Text Generation • Updated • 107k • 568
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 85.2k • 1k -
google/gemma-3-4b-it
Image-Text-to-Text • Updated • 1.63M • 1.27k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 173k • 151 -
google/gemma-3-1b-pt
Text Generation • Updated • 67k • 187 -
google/gemma-3-1b-it
Text Generation • Updated • 1.5M • 895 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 29.3k • 88 -
google/gemma-3-12b-it
Image-Text-to-Text • Updated • 2.57M • • 698 -
google/gemma-3-27b-pt
Image-Text-to-Text • Updated • 16.6k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 1.06M • • 1.94kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 4.98k • 155Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 14.9k • 249 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 109 • 24 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.49k • 121 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 40 • 12 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 8.17k • 262 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 95 • 19 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 5.21k • 399
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 73 • 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 • 42 • 8 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 200 • 12 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 461 • 10 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 4.98k • 39 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 28.2k • • 81 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 297 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 200 • 9 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 715 • 11
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 575 • 13Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision