google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 54.6k • 715
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 94.7k • 1.15k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.02M • • 1.66k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 285k • • 180 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 40.5k • • 225 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 207k • • 1.31k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 42.4k • • 97 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 393k • • 913 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 8.38k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 339k • • 2.07kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 11.2k • 190Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 6.03k • 335 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 35 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.25k • 184 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 57 • 17 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.53k • 304 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 55 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 398 • 408
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 34 • 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 • 31 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 77 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 84 • 13 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 47 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 7.92k • • 221 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 923 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 30 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 45 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 98 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision