Geekbench ML Score

1488
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date March 08 2025 05:22 AM
Views 5

System Information

System Information
Operating System iOS 18.3
Model iPhone17,5
Model IDiPhone17,5
Motherboard V59AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 1.61 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.54 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1154
123.6 IPS
 
Image Classification (F16)
100% 1106
118.5 IPS
 
Image Classification (I8)
81% 634
67.9 IPS
 
Image Segmentation (F32)
100% 1708
10.5 IPS
 
Image Segmentation (F16)
100% 1643
10.1 IPS
 
Image Segmentation (I8)
89% 1752
10.8 IPS
 
Pose Estimation (F32)
100% 498
2.01 IPS
 
Pose Estimation (F16)
100% 489
1.98 IPS
 
Pose Estimation (I8)
80% 670
2.71 IPS
 
Object Detection (F32)
100% 1529
53.7 IPS
 
Object Detection (F16)
100% 1525
53.5 IPS
 
Object Detection (I8)
52% 966
33.9 IPS
 
Face Detection (F32)
100% 1951
22.4 IPS
 
Face Detection (F16)
100% 1861
21.4 IPS
 
Face Detection (I8)
75% 1210
13.9 IPS
 
Text Classification (F32)
100% 5730
2.27 KIPS
 
Text Classification (F16)
100% 5914
2.34 KIPS
 
Machine Translation (F32)
100% 3017
464.9 IPS
 
Machine Translation (F16)
100% 2931
451.8 IPS
 

Compare

Set Baseline Geekbench 6 now available