google/gemma-3-270m-it
Text Generation
•
0.3B
•
Updated
•
145k
•
508
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 46.7k • 943 -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 772k • 1.07k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 49.3k • 132 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 41.5k • 172 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 2.34M • 783 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 21k • 79 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 1.36M • • 601 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 14.3k • 115
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 1.54M • • 1.79kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 2.3k • 137Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 10.5k • 224 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 146 • 23 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.25k • 111 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 102 • 12 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 76.8k • 226 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 66 • 17 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 17k • 372
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 49 • 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 • 278 • 8 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 492 • 12 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 583 • 10 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 471 • 37 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 1.02k • • 16 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 342 • 9 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 520 • 9 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 307 • 11
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 1.37k • 12Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision