Geekbench ML Score

2782
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 29 2023 05:18 PM
Views 1

System Information

System Information
Operating System iOS 17.1
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 7.47 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2940
315.0 IPS
 
Image Classification (F16)
100% 4972
532.8 IPS
 
Image Classification (I8)
81% 834
89.3 IPS
 
Image Segmentation (F32)
100% 6141
37.9 IPS
 
Image Segmentation (F16)
100% 9923
61.3 IPS
 
Image Segmentation (I8)
89% 1541
9.52 IPS
 
Pose Estimation (F32)
100% 2449
9.91 IPS
 
Pose Estimation (F16)
100% 5279
21.4 IPS
 
Pose Estimation (I8)
80% 287
1.16 IPS
 
Object Detection (F32)
100% 3810
133.7 IPS
 
Object Detection (F16)
100% 4457
156.4 IPS
 
Object Detection (I8)
52% 1201
42.1 IPS
 
Face Detection (F32)
100% 5950
68.4 IPS
 
Face Detection (F16)
97% 11059
127.1 IPS
 
Face Detection (I8)
75% 1178
13.5 IPS
 
Text Classification (F32)
100% 2142
847.2 IPS
 
Text Classification (F16)
100% 2371
937.8 IPS
 
Machine Translation (F32)
100% 2862
441.0 IPS
 
Machine Translation (F16)
100% 2841
437.8 IPS
 

Compare

Set Baseline Geekbench 6 now available