Geekbench ML Score

1008
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 08:42 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.45 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 855
91.6 IPS
 
Image Classification (F16)
100% 813
87.1 IPS
 
Image Classification (I8)
81% 476
51.0 IPS
 
Image Segmentation (F32)
100% 1292
7.98 IPS
 
Image Segmentation (F16)
100% 1271
7.85 IPS
 
Image Segmentation (I8)
89% 1506
9.30 IPS
 
Pose Estimation (F32)
100% 476
1.92 IPS
 
Pose Estimation (F16)
100% 469
1.90 IPS
 
Pose Estimation (I8)
80% 538
2.18 IPS
 
Object Detection (F32)
100% 1210
42.5 IPS
 
Object Detection (F16)
100% 1220
42.8 IPS
 
Object Detection (I8)
52% 777
27.3 IPS
 
Face Detection (F32)
100% 1522
17.5 IPS
 
Face Detection (F16)
100% 1493
17.2 IPS
 
Face Detection (I8)
75% 859
9.87 IPS
 
Text Classification (F32)
100% 997
394.2 IPS
 
Text Classification (F16)
100% 1056
417.8 IPS
 
Machine Translation (F32)
100% 2245
346.0 IPS
 
Machine Translation (F16)
100% 2263
348.8 IPS
 

Compare

Set Baseline