mlx-community/gemma-3-27b-it-qat-bf16
Image-Text-to-Text
•
Updated
•
118
•
2
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 • 286 • 2 -
mlx-community/gemma-3-27b-it-qat-6bit
Image-Text-to-Text • Updated • 88 -
mlx-community/gemma-3-27b-it-qat-4bit
Image-Text-to-Text • Updated • 1.28k • 9 -
mlx-community/gemma-3-27b-it-qat-3bit
Image-Text-to-Text • Updated • 144 • 2 -
mlx-community/gemma-3-12b-it-qat-bf16
Image-Text-to-Text • Updated • 25 -
mlx-community/gemma-3-12b-it-qat-8bit
Image-Text-to-Text • Updated • 86 -
mlx-community/gemma-3-12b-it-qat-6bit
Image-Text-to-Text • Updated • 48 -
mlx-community/gemma-3-12b-it-qat-4bit
Image-Text-to-Text • Updated • 551 • 3 -
mlx-community/gemma-3-12b-it-qat-3bit
Image-Text-to-Text • Updated • 42 • 1 -
mlx-community/gemma-3-4b-it-qat-bf16
Image-Text-to-Text • Updated • 33 -
mlx-community/gemma-3-4b-it-qat-8bit
Image-Text-to-Text • Updated • 54 -
mlx-community/gemma-3-4b-it-qat-4bit
Image-Text-to-Text • Updated • 311 • 1 -
mlx-community/gemma-3-4b-it-qat-3bit
Image-Text-to-Text • Updated • 40 -
mlx-community/gemma-3-1b-it-qat-bf16
Text Generation • Updated • 41 -
mlx-community/gemma-3-1b-it-qat-8bit
Text Generation • Updated • 62 -
mlx-community/gemma-3-1b-it-qat-6bit
Text Generation • Updated • 23 -
mlx-community/gemma-3-4b-it-qat-6bit
Image-Text-to-Text • Updated • 23 -
mlx-community/gemma-3-1b-it-qat-4bit
Text Generation • Updated • 182 • 1