Geekbench ML Score

884
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 09:05 PM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 12 Mini
Model IDiPhone13,1
Motherboard D52gAP
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 3.63 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 632
67.7 IPS
 
Image Classification (F16)
100% 623
66.8 IPS
 
Image Classification (I8)
81% 415
44.5 IPS
 
Image Segmentation (F32)
100% 968
5.98 IPS
 
Image Segmentation (F16)
100% 944
5.83 IPS
 
Image Segmentation (I8)
89% 1376
8.50 IPS
 
Pose Estimation (F32)
100% 367
1.49 IPS
 
Pose Estimation (F16)
100% 356
1.44 IPS
 
Pose Estimation (I8)
80% 434
1.76 IPS
 
Object Detection (F32)
100% 876
30.8 IPS
 
Object Detection (F16)
100% 879
30.8 IPS
 
Object Detection (I8)
52% 702
24.6 IPS
 
Face Detection (F32)
100% 1079
12.4 IPS
 
Face Detection (F16)
100% 1053
12.1 IPS
 
Face Detection (I8)
75% 814
9.35 IPS
 
Text Classification (F32)
100% 2430
961.1 IPS
 
Text Classification (F16)
100% 2433
962.2 IPS
 
Machine Translation (F32)
100% 1679
258.8 IPS
 
Machine Translation (F16)
100% 1677
258.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download