google/gemma-3-270m-it
Text Generation • Updated • 137k • 578
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 102k • 1.02k -
google/gemma-3-4b-it
Image-Text-to-Text • Updated • 1.87M • 1.31k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 171k • 154 -
google/gemma-3-1b-pt
Text Generation • Updated • 69.5k • 192 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 635k • 929 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 19.7k • 89 -
google/gemma-3-12b-it
Image-Text-to-Text • Updated • 2.52M • • 708 -
google/gemma-3-27b-pt
Image-Text-to-Text • Updated • 14k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 568k • • 1.96kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 4.17k • 160Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 11.3k • 255 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 466 • 26 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.11k • 125 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 84 • 14 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 5.63k • 266 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 42 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 1.88k • 399
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 46 • 31Note ^ 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 • 108 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 199 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 562 • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 36.1k • 41 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 48.8k • • 91 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 384 • 11 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 128 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 612 • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 222 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision