google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 849k • 607
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 1.92M • 1.05k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 2.13M • • 1.43k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 65.7k • 158 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 59.1k • • 196 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 3.05M • • 1.07k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 29.5k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.22M • • 793 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 9.89k • 124
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 842k • • 2kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 6.57k • 166Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 2.35k • 272 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 46 • 27 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.13k • 142 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 35 • 15 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.65k • 287 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 87 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 232 • 400
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 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 • 114 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 642 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 1.95k • • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 302 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 100k • • 151 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 65 • • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 24 • • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 371 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 143 • • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision