Geekbench ML Score

883
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 06:51 AM
Views 2

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 12
Model IDiPhone13,2
Motherboard D53gAP
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 3.62 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 647
69.3 IPS
 
Image Classification (F16)
100% 615
65.9 IPS
 
Image Classification (I8)
81% 404
43.3 IPS
 
Image Segmentation (F32)
100% 968
5.98 IPS
 
Image Segmentation (F16)
100% 943
5.82 IPS
 
Image Segmentation (I8)
89% 1405
8.68 IPS
 
Pose Estimation (F32)
100% 361
1.46 IPS
 
Pose Estimation (F16)
100% 360
1.46 IPS
 
Pose Estimation (I8)
80% 439
1.78 IPS
 
Object Detection (F32)
100% 875
30.7 IPS
 
Object Detection (F16)
100% 889
31.2 IPS
 
Object Detection (I8)
52% 729
25.6 IPS
 
Face Detection (F32)
100% 1085
12.5 IPS
 
Face Detection (F16)
100% 1071
12.3 IPS
 
Face Detection (I8)
75% 810
9.31 IPS
 
Text Classification (F32)
100% 2271
898.3 IPS
 
Text Classification (F16)
100% 2325
919.7 IPS
 
Machine Translation (F32)
100% 1686
259.8 IPS
 
Machine Translation (F16)
100% 1683
259.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download