Geekbench ML Score

1003
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 11:16 AM
Views 1

System Information

System Information
Operating System iOS 16.1.2
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% 832
89.1 IPS
 
Image Classification (F16)
100% 819
87.7 IPS
 
Image Classification (I8)
81% 488
52.3 IPS
 
Image Segmentation (F32)
100% 1263
7.80 IPS
 
Image Segmentation (F16)
100% 1237
7.64 IPS
 
Image Segmentation (I8)
89% 1478
9.13 IPS
 
Pose Estimation (F32)
100% 469
1.90 IPS
 
Pose Estimation (F16)
100% 465
1.88 IPS
 
Pose Estimation (I8)
80% 533
2.16 IPS
 
Object Detection (F32)
100% 1202
42.2 IPS
 
Object Detection (F16)
100% 1203
42.2 IPS
 
Object Detection (I8)
52% 783
27.5 IPS
 
Face Detection (F32)
100% 1512
17.4 IPS
 
Face Detection (F16)
100% 1481
17.0 IPS
 
Face Detection (I8)
75% 862
9.90 IPS
 
Text Classification (F32)
100% 1069
422.7 IPS
 
Text Classification (F16)
100% 983
388.8 IPS
 
Machine Translation (F32)
100% 2269
349.8 IPS
 
Machine Translation (F16)
100% 2278
351.0 IPS
 

Compare

Set Baseline