google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 165k • 590
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 5.39M • 1.03k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.92M • 1.34k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 510k • 155 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 103k • • 195 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 1.32M • • 966 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 18.9k • 90 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 2.85M • 721 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 8.87k • 122
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 1.29M • • 1.97kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 4.15k • 163Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 10.1k • 261 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 55 • 26 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 748 • 128 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 41 • 14 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 4.48k • 273 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 67 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 429 • 400
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 13 • 31Note ^ 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 • 123 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 145 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 878 • • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 104k • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 68.3k • • 115 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 39 • • 11 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 532 • • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 104 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 24 • • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision