google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 74.6k • 696
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 68.1k • 1.13k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 960k • • 1.6k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 254k • • 172 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 37.9k • • 218 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 827k • • 1.27k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 54.6k • • 97 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 333k • • 884 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 10.1k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 341k • • 2.06kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 6.78k • 184Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 3.19k • 317 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 46 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.02k • 175 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 60 • 17 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.58k • 303 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 45 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 440 • 407
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 29 • 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 • 26 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 81 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 106 • 13 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 56 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 5.88k • • 209 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 479 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 46 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 82 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 78 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision