google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 77.8k • 700
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 68.9k • 1.13k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 956k • • 1.61k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 298k • • 172 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 37.4k • • 220 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 681k • • 1.28k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 57.3k • • 97 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 344k • • 896 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 11.5k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 339k • • 2.06kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 6.55k • 186Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 6.33k • 321 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 49 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.06k • 177 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 80 • 17 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.58k • 304 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 48 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 449 • 407
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 31 • 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 • 28 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 81 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 116 • 13 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 51 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 5.9k • • 210 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 576 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 46 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 80 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 84 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision