google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 82.4k • 656
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 58.4k • 1.11k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.23M • • 1.57k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 129k • • 172 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 55.1k • • 214 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 3.14M • • 1.21k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 28.8k • • 96 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 439k • • 859 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 10.3k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 418k • • 2.05kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 9.35k • 176Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 2.7k • 303 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 47 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 967 • 170 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 79 • 17 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 673 • 297 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 38 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 389 • 406
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 11 • 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 • 26 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 63 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 154 • 12 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 186 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 11.3k • • 200 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 1.23k • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 37 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 57 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 62 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision