google/gemma-3-27b-it

Image-Text-to-Text • 27B • Updated Mar 21, 2025 • 1.19M • • 1.93k

Note ^ transformers-based pre-trained and instruct models

google/shieldgemma-2-4b-it

Image-Text-to-Text • Updated Apr 4, 2025 • 9.08k • 153

Note ^ ShieldGemma 2

google/gemma-3-27b-pt-qat-q4_0-gguf

Image-Text-to-Text • 27B • Updated Apr 3, 2025 • 97 • 30

Note ^ GGUFs to be used in llama.cpp and Ollama. We strongly recommend using the IT models.

google/gemma-3-1b-it-qat-int4-unquantized

Text Generation • 1.0B • Updated Apr 15, 2025 • 670 • 13

Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision