mlx-community/gemma-3-27b-it-qat-bf16
Image-Text-to-Text
•
Updated
•
224
•
3
Gemma 3 QAT
Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory.
-
-
mlx-community/gemma-3-27b-it-qat-8bit
Image-Text-to-Text • Updated • 540 • 3 -
mlx-community/gemma-3-27b-it-qat-6bit
Image-Text-to-Text • Updated • 164 -
mlx-community/gemma-3-27b-it-qat-4bit
Image-Text-to-Text • Updated • 3.02k • 16 -
mlx-community/gemma-3-27b-it-qat-3bit
Image-Text-to-Text • Updated • 282 • 2 -
mlx-community/gemma-3-12b-it-qat-bf16
Image-Text-to-Text • Updated • 37 -
mlx-community/gemma-3-12b-it-qat-8bit
Image-Text-to-Text • Updated • 171 -
mlx-community/gemma-3-12b-it-qat-6bit
Image-Text-to-Text • Updated • 95 -
mlx-community/gemma-3-12b-it-qat-4bit
Image-Text-to-Text • Updated • 1.42k • 6 -
mlx-community/gemma-3-12b-it-qat-3bit
Image-Text-to-Text • Updated • 87 • 1 -
mlx-community/gemma-3-4b-it-qat-bf16
Image-Text-to-Text • Updated • 62 -
mlx-community/gemma-3-4b-it-qat-8bit
Image-Text-to-Text • Updated • 126 -
mlx-community/gemma-3-4b-it-qat-4bit
Image-Text-to-Text • Updated • 808 • 2 -
mlx-community/gemma-3-4b-it-qat-3bit
Image-Text-to-Text • Updated • 61 -
mlx-community/gemma-3-1b-it-qat-bf16
Text Generation • Updated • 71 -
mlx-community/gemma-3-1b-it-qat-8bit
Text Generation • Updated • 135 -
mlx-community/gemma-3-1b-it-qat-6bit
Text Generation • Updated • 48 -
mlx-community/gemma-3-4b-it-qat-6bit
Image-Text-to-Text • Updated • 39 -
mlx-community/gemma-3-1b-it-qat-4bit
Text Generation • Updated • 557 • 2