google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 74.6k • 645
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 89.7k • 1.11k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.51M • • 1.54k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 119k • • 171 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 61.4k • • 208 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 3.29M • • 1.19k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 35.1k • • 94 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 537k • • 845 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 12.6k • • 125
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 411k • • 2.04kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 10.4k • 174Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 2.66k • 294 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 39 • 28 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 876 • 160 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 81 • 16 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 716 • 298 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 29 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 381 • 404
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 30 • 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 • 53 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 122 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 155 • 12 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 570 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 16.2k • • 192 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 1.16k • 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 • 36 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 68 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision