google/gemma-3-27b-it

Image-Text-to-Text • 27B • Updated Mar 21, 2025 • 1.44M • • 1.97k

Note ^ transformers-based pre-trained and instruct models

google/shieldgemma-2-4b-it

Image-Text-to-Text • 4B • Updated Apr 4, 2025 • 4.72k • 164

Note ^ ShieldGemma 2

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

Image-Text-to-Text • 27B • Updated Apr 3, 2025 • 14 • 32

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 • 41 • • 14

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