Geekbench ML Score

327
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 17 2024 06:40 PM
Views 1

System Information

System Information
Operating System iOS 15.8.3
Model iPhone SE
Model IDiPhone8,4
Motherboard N69AP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.80 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.97 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 211
22.6 IPS
 
Image Classification (F16)
100% 211
22.6 IPS
 
Image Classification (I8)
81% 346
37.1 IPS
 
Image Segmentation (F32)
100% 399
2.46 IPS
 
Image Segmentation (F16)
100% 398
2.46 IPS
 
Image Segmentation (I8)
89% 646
3.99 IPS
 
Pose Estimation (F32)
100% 128
0.52 IPS
 
Pose Estimation (F16)
100% 122
0.49 IPS
 
Pose Estimation (I8)
80% 121
0.49 IPS
 
Object Detection (F32)
100% 350
12.3 IPS
 
Object Detection (F16)
100% 360
12.6 IPS
 
Object Detection (I8)
52% 474
16.6 IPS
 
Face Detection (F32)
100% 434
4.99 IPS
 
Face Detection (F16)
100% 428
4.92 IPS
 
Face Detection (I8)
75% 453
5.21 IPS
 
Text Classification (F32)
100% 465
183.7 IPS
 
Text Classification (F16)
100% 472
186.6 IPS
 
Machine Translation (F32)
100% 423
65.2 IPS
 
Machine Translation (F16)
100% 429
66.1 IPS
 

Compare

Set Baseline Geekbench 6 now available