Geekbench ML Score

1045
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 03:40 PM
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% 837
89.7 IPS
 
Image Classification (F16)
100% 839
89.9 IPS
 
Image Classification (I8)
81% 452
48.4 IPS
 
Image Segmentation (F32)
100% 1279
7.90 IPS
 
Image Segmentation (F16)
100% 1276
7.88 IPS
 
Image Segmentation (I8)
89% 1479
9.14 IPS
 
Pose Estimation (F32)
100% 478
1.93 IPS
 
Pose Estimation (F16)
100% 461
1.87 IPS
 
Pose Estimation (I8)
80% 543
2.20 IPS
 
Object Detection (F32)
100% 1265
44.4 IPS
 
Object Detection (F16)
100% 1269
44.5 IPS
 
Object Detection (I8)
52% 774
27.2 IPS
 
Face Detection (F32)
100% 1517
17.4 IPS
 
Face Detection (F16)
100% 1513
17.4 IPS
 
Face Detection (I8)
75% 856
9.84 IPS
 
Text Classification (F32)
100% 1498
592.5 IPS
 
Text Classification (F16)
100% 1350
533.8 IPS
 
Machine Translation (F32)
100% 2274
350.5 IPS
 
Machine Translation (F16)
100% 2268
349.6 IPS
 

Compare

Set Baseline