Text Generation • 0.3B • Updated • 51.1k
• 716
Text Generation • 0.3B • Updated • 91.2k
• 1.15k
Image-Text-to-Text • 4B • Updated • 1.01M
• • 1.67k
Image-Text-to-Text • 4B • Updated • 278k
• • 180
Text Generation • 1.0B • Updated • 39.9k
• • 224
Text Generation • 1.0B • Updated • 203k
• • 1.32k
Image-Text-to-Text • 12B • Updated • 33.4k
• • 97
Image-Text-to-Text • 12B • Updated • 404k
• • 916
Image-Text-to-Text • 27B • Updated • 7.92k
• • 126
Image-Text-to-Text • 27B • Updated • 326k
• • 2.07k
Note ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 11.3k
• 192
Note ^ ShieldGemma 2
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 5.95k
• 337
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 37
• 29
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.25k
• 187
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 58
• 17
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.52k
• 305
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 56
• 24
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 204
• 409
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 36
• 32
Note ^ 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 • 35
• 9
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 82
• 13
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 85
• 13
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 51
• • 42
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 7.94k
• • 224
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 946
• 10
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 34
• 10
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 51
• • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 73
• 14
Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision