google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 60.4k • 706
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 87.2k • 1.14k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 985k • • 1.62k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 291k • • 173 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 36.6k • • 221 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 188k • • 1.29k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 55.6k • • 97 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 359k • • 905 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 10.4k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 361k • • 2.07kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 6.72k • 188Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 6.1k • 328 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 37 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.33k • 180 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 67 • 17 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.76k • 304 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 42 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 467 • 408
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 37 • 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 • 29 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 80 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 112 • 13 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 55 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 6.55k • • 215 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 731 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 44 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 59 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 91 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision