Geekbench ML Score

922
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 05:26 PM
Views 1

System Information

System Information
Operating System iOS 15.2
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.53 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 769
82.4 IPS
 
Image Classification (F16)
100% 732
78.4 IPS
 
Image Classification (I8)
81% 455
48.7 IPS
 
Image Segmentation (F32)
100% 1078
6.66 IPS
 
Image Segmentation (F16)
100% 1045
6.46 IPS
 
Image Segmentation (I8)
89% 1441
8.90 IPS
 
Pose Estimation (F32)
100% 412
1.67 IPS
 
Pose Estimation (F16)
100% 410
1.66 IPS
 
Pose Estimation (I8)
80% 479
1.94 IPS
 
Object Detection (F32)
100% 1039
36.4 IPS
 
Object Detection (F16)
100% 1054
37.0 IPS
 
Object Detection (I8)
52% 742
26.0 IPS
 
Face Detection (F32)
100% 1282
14.7 IPS
 
Face Detection (F16)
100% 1257
14.4 IPS
 
Face Detection (I8)
75% 848
9.75 IPS
 
Text Classification (F32)
100% 1164
460.2 IPS
 
Text Classification (F16)
100% 1283
507.6 IPS
 
Machine Translation (F32)
100% 1968
303.3 IPS
 
Machine Translation (F16)
100% 1968
303.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download