Geekbench ML Score

581
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 04 2023 09:09 PM
Views 1

System Information

System Information
Operating System iOS 16.6.1
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 462
49.5 IPS
 
Image Classification (F16)
100% 456
48.9 IPS
 
Image Classification (I8)
81% 273
29.3 IPS
 
Image Segmentation (F32)
100% 755
4.66 IPS
 
Image Segmentation (F16)
100% 755
4.66 IPS
 
Image Segmentation (I8)
89% 962
5.94 IPS
 
Pose Estimation (F32)
100% 239
0.97 IPS
 
Pose Estimation (F16)
100% 241
0.97 IPS
 
Pose Estimation (I8)
80% 265
1.07 IPS
 
Object Detection (F32)
100% 700
24.6 IPS
 
Object Detection (F16)
100% 701
24.6 IPS
 
Object Detection (I8)
52% 533
18.7 IPS
 
Face Detection (F32)
100% 869
9.99 IPS
 
Face Detection (F16)
100% 811
9.32 IPS
 
Face Detection (I8)
75% 628
7.22 IPS
 
Text Classification (F32)
100% 774
306.2 IPS
 
Text Classification (F16)
100% 776
307.1 IPS
 
Machine Translation (F32)
100% 1002
154.5 IPS
 
Machine Translation (F16)
100% 999
154.0 IPS
 

Compare

Set Baseline Geekbench 6 now available