Geekbench ML Score

475
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 30 2025 12:36 AM
Views 7

System Information

System Information
Operating System iOS 15.8.3
Model iPhone 6s
Model IDiPhone8,1
Motherboard N71AP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.85 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.96 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 474
50.8 IPS
 
Image Classification (F16)
100% 664
71.2 IPS
 
Image Classification (I8)
81% 139
14.9 IPS
 
Image Segmentation (F32)
100% 1171
7.23 IPS
 
Image Segmentation (F16)
100% 1908
11.8 IPS
 
Image Segmentation (I8)
89% 269
1.66 IPS
 
Pose Estimation (F32)
100% 454
1.84 IPS
 
Pose Estimation (F16)
100% 859
3.47 IPS
 
Pose Estimation (I8)
80% 52
0.21 IPS
 
Object Detection (F32)
100% 682
23.9 IPS
 
Object Detection (F16)
100% 910
31.9 IPS
 
Object Detection (I8)
52% 215
7.55 IPS
 
Face Detection (F32)
100% 1125
12.9 IPS
 
Face Detection (F16)
97% 1974
22.7 IPS
 
Face Detection (I8)
75% 202
2.32 IPS
 
Text Classification (F32)
100% 403
159.5 IPS
 
Text Classification (F16)
98% 501
198.1 IPS
 
Machine Translation (F32)
100% 333
51.4 IPS
 
Machine Translation (F16)
100% 348
53.7 IPS
 

Compare

Set Baseline Geekbench 6 now available