google/gemma-3-270m-it
Text Generation • Updated • 123k • 569
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 77.7k • 1k -
google/gemma-3-4b-it
Image-Text-to-Text • Updated • 1.53M • 1.28k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 169k • 153 -
google/gemma-3-1b-pt
Text Generation • Updated • 66.1k • 188 -
google/gemma-3-1b-it
Text Generation • Updated • 1.26M • 900 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 20.8k • 88 -
google/gemma-3-12b-it
Image-Text-to-Text • Updated • 2.63M • • 700 -
google/gemma-3-27b-pt
Image-Text-to-Text • Updated • 17.9k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 922k • • 1.94kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 3.56k • 155Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 13.8k • 250 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 145 • 24 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.26k • 121 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 41 • 12 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 6.74k • 263 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 79 • 20 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 3.34k • 399
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 66 • 30Note ^ 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 • 101 • 8 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 205 • 12 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 660 • 10 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 380 • 39 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 31.1k • • 83 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 331 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 179 • 9 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 734 • 11
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 519 • 13Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision