Geekbench ML Score

2516
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date February 22 2023 09:14 AM
Views 2

System Information

System Information
Operating System iOS 16.3.1
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.44 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2875
308.1 IPS
 
Image Classification (F16)
100% 4702
503.8 IPS
 
Image Classification (I8)
81% 743
79.6 IPS
 
Image Segmentation (F32)
100% 6370
39.3 IPS
 
Image Segmentation (F16)
100% 8751
54.1 IPS
 
Image Segmentation (I8)
89% 1361
8.41 IPS
 
Pose Estimation (F32)
100% 2359
9.55 IPS
 
Pose Estimation (F16)
100% 5044
20.4 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 3363
118.0 IPS
 
Object Detection (F16)
100% 3646
128.0 IPS
 
Object Detection (I8)
52% 1058
37.1 IPS
 
Face Detection (F32)
100% 5807
66.7 IPS
 
Face Detection (F16)
97% 9895
113.7 IPS
 
Face Detection (I8)
75% 1044
12.0 IPS
 
Text Classification (F32)
100% 2017
797.6 IPS
 
Text Classification (F16)
100% 2177
861.2 IPS
 
Machine Translation (F32)
100% 2264
348.9 IPS
 
Machine Translation (F16)
100% 2270
349.8 IPS
 

Compare

Set Baseline Geekbench 6 now available