Text Generation
• Updated Aug 14, 2025 • 165k
• 579
Text Generation
• 0.3B • Updated Aug 14, 2025 • 102k
• 1.02k
Image-Text-to-Text
• Updated Mar 21, 2025 • 2.01M
• 1.31k
Image-Text-to-Text
• 4B • Updated Mar 21, 2025 • 180k
• 154
Text Generation
• Updated Mar 21, 2025 • 81.4k
• 192
Text Generation
• 1.0B • Updated Apr 4, 2025 • 578k
• 931
Image-Text-to-Text
• 12B • Updated Mar 21, 2025 • 18.9k
• 89
Image-Text-to-Text
• Updated Mar 21, 2025 • 2.54M
• • 709
Image-Text-to-Text
• Updated Mar 21, 2025 • 13.6k
• 123
Image-Text-to-Text
• 27B • Updated Mar 21, 2025 • 497k
• • 1.96k
Note ^ transformers-based pre-trained and instruct models
google/shieldgemma-2-4b-it Image-Text-to-Text
• Updated Apr 4, 2025 • 4.07k
• 160
Note ^ ShieldGemma 2
google/gemma-3-4b-it-qat-q4_0-gguf Image-Text-to-Text
• 4B • Updated Apr 11, 2025 • 11.2k
• 256
google/gemma-3-4b-pt-qat-q4_0-gguf Image-Text-to-Text
• 4B • Updated Apr 3, 2025 • 476
• 26
google/gemma-3-1b-it-qat-q4_0-gguf Text Generation
• 1.0B • Updated Apr 11, 2025 • 1.08k
• 125
google/gemma-3-1b-pt-qat-q4_0-gguf Text Generation
• 1.0B • Updated Apr 3, 2025 • 84
• 14
google/gemma-3-12b-it-qat-q4_0-gguf Image-Text-to-Text
• 12B • Updated Apr 11, 2025 • 5.47k
• 266
google/gemma-3-12b-pt-qat-q4_0-gguf Image-Text-to-Text
• 12B • Updated Apr 3, 2025 • 40
• 21
google/gemma-3-27b-it-qat-q4_0-gguf Image-Text-to-Text
• 27B • Updated Apr 11, 2025 • 1.68k
• 399
google/gemma-3-27b-pt-qat-q4_0-gguf Image-Text-to-Text
• 27B • Updated Apr 3, 2025 • 23
• 31
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 Aug 14, 2025 • 109
• 9
google/gemma-3-270m-it-qat-q4_0-unquantized Text Generation
• 0.3B • Updated Aug 14, 2025 • 215
• 13
google/gemma-3-4b-it-qat-q4_0-unquantized Image-Text-to-Text
• 4B • Updated Apr 15, 2025 • 579
• 11
google/gemma-3-27b-it-qat-q4_0-unquantized Image-Text-to-Text
• Updated Apr 15, 2025 • 48.4k
• 41
google/gemma-3-12b-it-qat-q4_0-unquantized Image-Text-to-Text
• Updated Apr 15, 2025 • 51.1k
• • 91
google/gemma-3-1b-it-qat-q4_0-unquantized Text Generation
• 1.0B • Updated Apr 15, 2025 • 376
• 11
google/gemma-3-4b-it-qat-int4-unquantized Image-Text-to-Text
• Updated Apr 15, 2025 • 248
• 10
google/gemma-3-12b-it-qat-int4-unquantized Image-Text-to-Text
• 12B • Updated Apr 15, 2025 • 562
• 12
google/gemma-3-1b-it-qat-int4-unquantized Text Generation
• 1.0B • Updated Apr 15, 2025 • 204
• 14
Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision