google/gemma-3-270m-it
Text Generation • Updated • 125k • 577
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 93.2k • 1.01k -
google/gemma-3-4b-it
Image-Text-to-Text • Updated • 1.73M • 1.3k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 134k • 154 -
google/gemma-3-1b-pt
Text Generation • Updated • 69.7k • 190 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 805k • 917 -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 20.6k • 89 -
google/gemma-3-12b-it
Image-Text-to-Text • Updated • 2.53M • • 704 -
google/gemma-3-27b-pt
Image-Text-to-Text • Updated • 15.8k • 123
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 728k • • 1.95kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • Updated • 3.83k • 158Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 12.2k • 254 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 479 • 25 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.22k • 123 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 82 • 14 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 5.62k • 266 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 50 • 21 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 2.71k • 399
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 63 • 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 • 94 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 201 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 605 • 11 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 9.8k • 41 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 41.8k • • 85 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 352 • 11 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 159 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 747 • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 254 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision