Geekbench ML Score

386
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 19 2024 07:05 AM
Views 1

System Information

System Information
Operating System iOS 15.8.3
Model iPhone 7
Model IDiPhone9,1
Motherboard D10AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.95 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 271
29.1 IPS
 
Image Classification (F16)
100% 270
28.9 IPS
 
Image Classification (I8)
81% 466
49.9 IPS
 
Image Segmentation (F32)
100% 470
2.90 IPS
 
Image Segmentation (F16)
100% 482
2.97 IPS
 
Image Segmentation (I8)
89% 787
4.86 IPS
 
Pose Estimation (F32)
100% 143
0.58 IPS
 
Pose Estimation (F16)
100% 127
0.51 IPS
 
Pose Estimation (I8)
80% 166
0.67 IPS
 
Object Detection (F32)
100% 395
13.9 IPS
 
Object Detection (F16)
100% 401
14.1 IPS
 
Object Detection (I8)
52% 624
21.9 IPS
 
Face Detection (F32)
100% 501
5.76 IPS
 
Face Detection (F16)
100% 481
5.52 IPS
 
Face Detection (I8)
75% 511
5.87 IPS
 
Text Classification (F32)
100% 462
182.8 IPS
 
Text Classification (F16)
100% 485
191.6 IPS
 
Machine Translation (F32)
100% 515
79.3 IPS
 
Machine Translation (F16)
100% 560
86.3 IPS
 

Compare

Set Baseline Geekbench 6 now available