google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 88.7k • 610
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 1.55M • 1.07k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.29M • • 1.46k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 72.3k • 159 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 62.9k • • 196 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 5M • • 1.1k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 33.7k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.23M • • 806 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 9.83k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 735k • • 2.01kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 7.95k • 166Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 3.58k • 278 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 19 • 27 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 912 • 146 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 48 • 15 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.13k • 291 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 19 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 394 • 400
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 5 • 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 • 142 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 356 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 512 • • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 131 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 86.2k • • 161 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 110 • • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 177 • • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 170 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 117 • • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision