Geekbench ML Score

274
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 09 2024 03:50 PM
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% 293
31.4 IPS
 
Image Classification (F16)
100% 271
29.1 IPS
 
Image Classification (I8)
81% 510
54.7 IPS
 
Image Segmentation (F32)
100% 442
2.73 IPS
 
Image Segmentation (F16)
100% 333
2.06 IPS
 
Image Segmentation (I8)
89% 484
2.99 IPS
 
Pose Estimation (F32)
100% 83
0.34 IPS
 
Pose Estimation (F16)
100% 83
0.34 IPS
 
Pose Estimation (I8)
80% 109
0.44 IPS
 
Object Detection (F32)
100% 250
8.77 IPS
 
Object Detection (F16)
100% 242
8.51 IPS
 
Object Detection (I8)
52% 377
13.2 IPS
 
Face Detection (F32)
100% 333
3.83 IPS
 
Face Detection (F16)
100% 332
3.81 IPS
 
Face Detection (I8)
75% 359
4.13 IPS
 
Text Classification (F32)
100% 321
127.1 IPS
 
Text Classification (F16)
100% 321
126.8 IPS
 
Machine Translation (F32)
100% 327
50.4 IPS
 
Machine Translation (F16)
100% 317
48.9 IPS
 

Compare

Set Baseline Geekbench 6 now available