google/gemma-3-270m-it
Text Generation • 0.3B • Updated • 69.8k • 677
Gemma 3 Release
-
-
google/gemma-3-270m
Text Generation • 0.3B • Updated • 63.9k • 1.12k -
google/gemma-3-4b-it
Image-Text-to-Text • 4B • Updated • 1.1M • • 1.58k -
google/gemma-3-4b-pt
Image-Text-to-Text • 4B • Updated • 130k • • 172 -
google/gemma-3-1b-pt
Text Generation • 1.0B • Updated • 38.3k • • 218 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 1.82M • • 1.24k -
google/gemma-3-12b-pt
Image-Text-to-Text • 12B • Updated • 44.8k • • 96 -
google/gemma-3-12b-it
Image-Text-to-Text • 12B • Updated • 370k • • 874 -
google/gemma-3-27b-pt
Image-Text-to-Text • 27B • Updated • 10.3k • • 126
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 400k • • 2.05kNote ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 8.97k • 180Note ^ ShieldGemma 2
-
google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 2.96k • 307 -
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • 4B • Updated • 55 • 29 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 1.11k • 173 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • 1.0B • Updated • 48 • 17 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 1.53k • 301 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • 12B • Updated • 43 • 24 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 507 • 407
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 9 • 32Note ^ 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 • 24 • 9 -
google/gemma-3-270m-it-qat-q4_0-unquantized
Text Generation • 0.3B • Updated • 61 • 13 -
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • 4B • Updated • 196 • 12 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 167 • • 42 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 7.84k • • 207 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • 1.0B • Updated • 1.25k • 10 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • 4B • Updated • 53 • 10 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • 12B • Updated • 73 • • 12
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • 1.0B • Updated • 83 • 14Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision