Geekbench ML Score

1005
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 30 2022 02:48 AM
Views 1

System Information

System Information
Operating System iOS 16.1
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 845
90.5 IPS
 
Image Classification (F16)
100% 838
89.8 IPS
 
Image Classification (I8)
81% 476
51.0 IPS
 
Image Segmentation (F32)
100% 1249
7.72 IPS
 
Image Segmentation (F16)
100% 1241
7.67 IPS
 
Image Segmentation (I8)
89% 1501
9.27 IPS
 
Pose Estimation (F32)
100% 471
1.91 IPS
 
Pose Estimation (F16)
100% 469
1.90 IPS
 
Pose Estimation (I8)
80% 541
2.19 IPS
 
Object Detection (F32)
100% 1215
42.7 IPS
 
Object Detection (F16)
100% 1218
42.7 IPS
 
Object Detection (I8)
52% 745
26.2 IPS
 
Face Detection (F32)
100% 1542
17.7 IPS
 
Face Detection (F16)
100% 1509
17.3 IPS
 
Face Detection (I8)
75% 864
9.93 IPS
 
Text Classification (F32)
100% 1012
400.2 IPS
 
Text Classification (F16)
100% 1026
405.6 IPS
 
Machine Translation (F32)
100% 2269
349.7 IPS
 
Machine Translation (F16)
100% 2272
350.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download