Geekbench ML Score

2495
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date June 10 2023 08:09 AM
Views 2

System Information

System Information
Operating System iOS 16.6
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.45 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% 2920
312.9 IPS
 
Image Classification (F16)
100% 4616
494.6 IPS
 
Image Classification (I8)
81% 738
79.1 IPS
 
Image Segmentation (F32)
100% 6431
39.7 IPS
 
Image Segmentation (F16)
100% 9332
57.6 IPS
 
Image Segmentation (I8)
89% 1312
8.10 IPS
 
Pose Estimation (F32)
100% 2380
9.63 IPS
 
Pose Estimation (F16)
100% 5126
20.7 IPS
 
Pose Estimation (I8)
80% 251
1.02 IPS
 
Object Detection (F32)
100% 3395
119.1 IPS
 
Object Detection (F16)
100% 3465
121.6 IPS
 
Object Detection (I8)
52% 1051
36.9 IPS
 
Face Detection (F32)
100% 5883
67.6 IPS
 
Face Detection (F16)
97% 9953
114.3 IPS
 
Face Detection (I8)
75% 1004
11.5 IPS
 
Text Classification (F32)
100% 2084
824.1 IPS
 
Text Classification (F16)
100% 1926
761.8 IPS
 
Machine Translation (F32)
100% 2240
345.2 IPS
 
Machine Translation (F16)
100% 2245
346.0 IPS
 

Compare

Set Baseline Geekbench 6 now available