Geekbench ML Score

878
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 06:10 AM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPhone 12 Pro Max
Model IDiPhone13,4
Motherboard D54pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.54 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 645
69.2 IPS
 
Image Classification (F16)
100% 617
66.2 IPS
 
Image Classification (I8)
81% 419
44.8 IPS
 
Image Segmentation (F32)
100% 1010
6.24 IPS
 
Image Segmentation (F16)
100% 995
6.15 IPS
 
Image Segmentation (I8)
89% 1394
8.61 IPS
 
Pose Estimation (F32)
100% 397
1.60 IPS
 
Pose Estimation (F16)
100% 386
1.56 IPS
 
Pose Estimation (I8)
80% 463
1.87 IPS
 
Object Detection (F32)
100% 913
32.0 IPS
 
Object Detection (F16)
100% 913
32.0 IPS
 
Object Detection (I8)
52% 730
25.6 IPS
 
Face Detection (F32)
100% 1108
12.7 IPS
 
Face Detection (F16)
100% 1079
12.4 IPS
 
Face Detection (I8)
75% 820
9.42 IPS
 
Text Classification (F32)
100% 1678
663.7 IPS
 
Text Classification (F16)
100% 1900
751.7 IPS
 
Machine Translation (F32)
100% 1636
252.2 IPS
 
Machine Translation (F16)
100% 1650
254.2 IPS
 

Compare

Set Baseline