Qualcomm® AI HubAI Hub
HomeCompute ModelsSESR-M5-Quantized

SESR-M5-Quantized

Upscale images in real time.

SESR M5 performs efficient on-device upscaling of images.

Snapdragon® X Elite
1.09ms
Inference Time
5MB
Memory Usage
29NPU
Layers

Technical Details

Model checkpoint:sesr_m5_4x_checkpoint
Input resolution:128x128
Number of parameters:338K
Model size:389 KB

Applicable Scenarios

  • Virtual Real Estate Tours
  • Gaming
  • ARVR

Licenses

Source Model:OTHER
Deployable Model:AI Model Hub License

Tags

  • quantized
    A “quantized” model can run in low or mixed precision, which can substantially reduce inference latency.

Supported Compute Chipsets

  • Snapdragon® X Elite