google/gemma-3-270m-it
Text Generation • Updated
• 110k • 552
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • Updated • 152k • 991 -
google/gemma-3-4b-it
Image-Text-to-Text • Updated • 1.65M • 1.2k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 107k • 147 -
google/gemma-3-1b-pt
Text Generation • Updated • 34.7k • 187 -
google/gemma-3-1b-it
Text Generation • Updated • 1.87M • 853 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 29.7k • 88 -
google/gemma-3-12b-it
Image-Text-to-Text • Updated • 1.2M • • 662 -
google/gemma-3-27b-pt
Image-Text-to-Text • Updated • 56.5k • 119
google/gemma-3-27b-it
Image-Text-to-Text • Updated • 1.66M • • 1.9kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 8.1k • 147Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 12.9k • 237 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 155 • 23 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.16k • 115 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 109 • 12 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 9.02k • 241 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 266 • 17 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 10k • 380
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 108 • 29Note ^ 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 • 172 • 8 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 531 • 12 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 771 • 10 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 1.35k • 38 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 13.2k • • 63 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 206 • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 418 • 9 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 10.6k • 11
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 835 • 13Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision