Text Generation • 0.3B • Updated • 41.1k
• 718
Text Generation • 0.3B • Updated • 94.6k
• 1.15k
Image-Text-to-Text • 4B • Updated • 991k
• • 1.68k
Image-Text-to-Text • 4B • Updated • 273k
• 180
Text Generation • 1.0B • Updated • 38.7k
• 227
Text Generation • 1.0B • Updated • 201k
• 1.33k
Image-Text-to-Text • 12B • Updated • 27.5k
• 97
Image-Text-to-Text • 12B • Updated • 409k
• • 924
Image-Text-to-Text • 27B • Updated • 7.51k
• 126
Image-Text-to-Text • 27B • Updated • 299k
• • 2.07k
Note ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 11.5k
• 192
Note ^ ShieldGemma 2
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 5.76k
• 341
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 34
• 30
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.23k
• 187
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 54
• 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 • 42
• 24
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 217
• 410
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 23
• 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 • 33
• 9
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 74
• 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 • 52
• 42
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 8.32k
• 226
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 936
• 10
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 35
• 10
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 37
• 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 63
• 14
Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision