google/gemma-3-270m-it
Text Generation
•
0.3B
•
Updated
•
141k
•
512
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 45.8k • 944 -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 756k • 1.08k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 137k • 135 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 39.6k • 173 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 2.33M • 785 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 20.5k • 79 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.32M • • 605 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 13.8k • 115
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 1.52M • • 1.79kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 2.24k • 137Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 10.2k • 224 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 117 • 23 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.25k • 113 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 93 • 12 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 71.6k • 226 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 60 • 17 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 4.18k • 372
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 45 • 28Note ^ 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 • 282 • 8 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 496 • 12 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 586 • 10 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 470 • 37 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 985 • • 16 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 330 • 9 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 521 • 9 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 306 • 11
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 1.21k • 12Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision