Geekbench ML Score

1420
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 25 2024 12:43 PM
Views 1

System Information

System Information
Operating System iOS 17.6
Model iPhone16,2
Model IDiPhone16,2
Motherboard D84AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.78 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.44 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1082
116.0 IPS
 
Image Classification (F16)
100% 1059
113.5 IPS
 
Image Classification (I8)
81% 654
70.1 IPS
 
Image Segmentation (F32)
100% 1463
9.04 IPS
 
Image Segmentation (F16)
100% 1436
8.87 IPS
 
Image Segmentation (I8)
89% 1675
10.3 IPS
 
Pose Estimation (F32)
100% 514
2.08 IPS
 
Pose Estimation (F16)
100% 507
2.05 IPS
 
Pose Estimation (I8)
80% 660
2.67 IPS
 
Object Detection (F32)
100% 1454
51.0 IPS
 
Object Detection (F16)
100% 1466
51.5 IPS
 
Object Detection (I8)
52% 933
32.8 IPS
 
Face Detection (F32)
100% 1891
21.7 IPS
 
Face Detection (F16)
100% 1869
21.5 IPS
 
Face Detection (I8)
75% 1034
11.9 IPS
 
Text Classification (F32)
100% 5447
2.15 KIPS
 
Text Classification (F16)
100% 5412
2.14 KIPS
 
Machine Translation (F32)
100% 2829
436.0 IPS
 
Machine Translation (F16)
100% 2852
439.6 IPS
 

Compare

Set Baseline Geekbench 6 now available