Paused Agents 13 Depth Anything V1 vs V2 π 13 Generate depth maps from images using V1 and V2 models
Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory β’ 15 items β’ Updated 8 days ago β’ 219