google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 77.5k • 687
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 64.9k • 1.13k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.06M • • 1.59k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 177k • • 172 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 40.1k • • 218 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 1.4M • • 1.25k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 49.7k • • 96 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 352k • • 882 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 10.5k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 371k • • 2.05kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 8.13k • 180Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 3.13k • 311 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 43 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.05k • 173 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 47 • 17 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.55k • 303 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 40 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 499 • 407
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 22 • 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 • 23 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 76 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 171 • 13 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 65 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 6.47k • • 207 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 435 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 48 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 81 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 85 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision