Text Generation • 0.3B • Updated • 37.9k
• 728
Text Generation • 0.3B • Updated • 91.5k
• 1.16k
Image-Text-to-Text • 4B • Updated • 1.1M
• • 1.7k
Image-Text-to-Text • 4B • Updated • 110k
• 180
Text Generation • 1.0B • Updated • 39k
• 232
Text Generation • 1.0B • Updated • 193k
• 1.34k
Image-Text-to-Text • 12B • Updated • 21.9k
• 97
Image-Text-to-Text • 12B • Updated • 406k
• • 925
Image-Text-to-Text • 27B • Updated • 5.97k
• 126
Image-Text-to-Text • 27B • Updated • 260k
• • 2.07k
Note ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 12.2k
• 192
Note ^ ShieldGemma 2
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 5.36k
• 344
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 25
• 30
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.22k
• 187
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 31
• 17
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.73k
• 305
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 29
• 25
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 311
• 411
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 10
• 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 • 39
• 9
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 65
• 13
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 97
• 13
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 57
• 42
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 8.47k
• 229
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 903
• 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 • 41
• 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 75
• 14
Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision