Geekbench ML Score

2410
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2022 06:10 AM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 1.67 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2786
298.5 IPS
 
Image Classification (F16)
100% 4519
484.1 IPS
 
Image Classification (I8)
81% 742
79.5 IPS
 
Image Segmentation (F32)
100% 6522
40.3 IPS
 
Image Segmentation (F16)
100% 8895
54.9 IPS
 
Image Segmentation (I8)
89% 1366
8.44 IPS
 
Pose Estimation (F32)
100% 2354
9.52 IPS
 
Pose Estimation (F16)
100% 5061
20.5 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 3366
118.1 IPS
 
Object Detection (F16)
100% 3570
125.3 IPS
 
Object Detection (I8)
52% 1066
37.4 IPS
 
Face Detection (F32)
100% 5881
67.6 IPS
 
Face Detection (F16)
97% 9849
113.2 IPS
 
Face Detection (I8)
75% 1047
12.0 IPS
 
Text Classification (F32)
100% 1323
523.4 IPS
 
Text Classification (F16)
100% 1535
607.1 IPS
 
Machine Translation (F32)
100% 2253
347.2 IPS
 
Machine Translation (F16)
100% 2246
346.1 IPS
 

Compare

Set Baseline