google/gemma-3-4b-it-qat-q4_0-gguf
Image-Text-to-Text
•
Updated
•
16.9k
•
113
Gemma 3 QAT
Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory
-
-
google/gemma-3-4b-pt-qat-q4_0-gguf
Image-Text-to-Text • Updated • 480 • 15 -
google/gemma-3-1b-it-qat-q4_0-gguf
Text Generation • Updated • 4.23k • 32 -
google/gemma-3-1b-pt-qat-q4_0-gguf
Text Generation • Updated • 203 • 6 -
google/gemma-3-12b-it-qat-q4_0-gguf
Image-Text-to-Text • Updated • 20.8k • 98 -
google/gemma-3-12b-pt-qat-q4_0-gguf
Image-Text-to-Text • Updated • 454 • 12 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • Updated • 66.6k • 233
google/gemma-3-27b-pt-qat-q4_0-gguf
Image-Text-to-Text • Updated • 560 • 22Note ^ GGUFs to be used in llama.cpp and Ollama. We strongly recommend using the IT models.
-
google/gemma-3-4b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 495 • 4 -
google/gemma-3-27b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 4.66k • 21 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • Updated • 467 • 9 -
google/gemma-3-1b-it-qat-q4_0-unquantized
Text Generation • Updated • 115 • 3 -
google/gemma-3-4b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 229 • 3 -
google/gemma-3-12b-it-qat-int4-unquantized
Image-Text-to-Text • Updated • 607 • 8
google/gemma-3-1b-it-qat-int4-unquantized
Text Generation • Updated • 411 • 3Note ^ unquantized QAT-based checkpoints that allow quantizing while retaining similar quality to half precision