Geekbench ML Score

555
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2022 12:07 AM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 465
49.9 IPS
 
Image Classification (F16)
100% 454
48.7 IPS
 
Image Classification (I8)
81% 256
27.4 IPS
 
Image Segmentation (F32)
100% 728
4.50 IPS
 
Image Segmentation (F16)
100% 719
4.44 IPS
 
Image Segmentation (I8)
89% 931
5.75 IPS
 
Pose Estimation (F32)
100% 212
0.86 IPS
 
Pose Estimation (F16)
100% 217
0.88 IPS
 
Pose Estimation (I8)
80% 261
1.05 IPS
 
Object Detection (F32)
100% 674
23.7 IPS
 
Object Detection (F16)
100% 679
23.8 IPS
 
Object Detection (I8)
52% 512
18.0 IPS
 
Face Detection (F32)
100% 788
9.05 IPS
 
Face Detection (F16)
100% 779
8.94 IPS
 
Face Detection (I8)
75% 587
6.74 IPS
 
Text Classification (F32)
100% 732
289.7 IPS
 
Text Classification (F16)
100% 733
289.9 IPS
 
Machine Translation (F32)
100% 989
152.4 IPS
 
Machine Translation (F16)
100% 988
152.2 IPS
 

Compare

Set Baseline