google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 75.2k • 645
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 89.2k • 1.11k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.45M • • 1.54k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 124k • • 171 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 61.2k • • 209 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 3.24M • • 1.2k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 35k • • 94 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 530k • • 845 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 12.1k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 415k • • 2.04kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 10.4k • 174Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 2.71k • 295 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 36 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 865 • 160 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 79 • 16 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 772 • 298 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 33 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 397 • 405
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 24 • 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 • 54 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 121 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 149 • 12 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 255 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 15.8k • • 192 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 1.16k • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 48 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 38 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 70 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision