Geekbench ML Score

999
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 09 2022 04:48 PM
Views 87

System Information

System Information
Operating System iOS 16.0
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.44 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 817
87.5 IPS
 
Image Classification (F16)
100% 809
86.7 IPS
 
Image Classification (I8)
81% 488
52.3 IPS
 
Image Segmentation (F32)
100% 1271
7.85 IPS
 
Image Segmentation (F16)
100% 1242
7.67 IPS
 
Image Segmentation (I8)
89% 1496
9.24 IPS
 
Pose Estimation (F32)
100% 466
1.89 IPS
 
Pose Estimation (F16)
100% 461
1.86 IPS
 
Pose Estimation (I8)
80% 527
2.13 IPS
 
Object Detection (F32)
100% 1207
42.4 IPS
 
Object Detection (F16)
100% 1198
42.0 IPS
 
Object Detection (I8)
52% 766
26.9 IPS
 
Face Detection (F32)
100% 1487
17.1 IPS
 
Face Detection (F16)
100% 1460
16.8 IPS
 
Face Detection (I8)
75% 859
9.87 IPS
 
Text Classification (F32)
100% 1077
425.8 IPS
 
Text Classification (F16)
100% 1016
402.0 IPS
 
Machine Translation (F32)
100% 2239
345.1 IPS
 
Machine Translation (F16)
100% 2256
347.8 IPS
 

Compare

Set Baseline