google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 92.9k • 622
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 843k • 1.09k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.67M • • 1.48k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 84.1k • 162 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 60.9k • 201 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 2.59M • • 1.14k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 36.6k • 91 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 713k • • 821 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 12.1k • 124
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 360k • • 2.02kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 9.22k • 169Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 2.63k • 283 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 34 • 28 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 823 • 152 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 76 • 16 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 913 • 296 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 23 • 22 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 409 • 401
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 27 • 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 • 147 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 330 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 132 • 12 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 497 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 69.7k • • 179 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 149 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 52 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 34 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 130 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision