Geekbench ML Score

981
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 23 2022 08:17 AM
Views 1

System Information

System Information
Operating System iOS 16.1
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
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 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 822
88.1 IPS
 
Image Classification (F16)
100% 809
86.7 IPS
 
Image Classification (I8)
81% 478
51.2 IPS
 
Image Segmentation (F32)
100% 1262
7.80 IPS
 
Image Segmentation (F16)
100% 1226
7.57 IPS
 
Image Segmentation (I8)
89% 1488
9.19 IPS
 
Pose Estimation (F32)
100% 462
1.87 IPS
 
Pose Estimation (F16)
100% 457
1.85 IPS
 
Pose Estimation (I8)
80% 519
2.10 IPS
 
Object Detection (F32)
100% 1176
41.3 IPS
 
Object Detection (F16)
100% 1182
41.5 IPS
 
Object Detection (I8)
52% 763
26.8 IPS
 
Face Detection (F32)
100% 1508
17.3 IPS
 
Face Detection (F16)
100% 1397
16.1 IPS
 
Face Detection (I8)
75% 838
9.63 IPS
 
Text Classification (F32)
100% 957
378.5 IPS
 
Text Classification (F16)
100% 950
375.7 IPS
 
Machine Translation (F32)
100% 2287
352.5 IPS
 
Machine Translation (F16)
100% 2268
349.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download