Geekbench ML Score

4500
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 15 2024 12:27 AM
Views 1

System Information

System Information
Operating System iOS 18.0.1
Model iPhone17,1
Model IDiPhone17,1
Motherboard D93AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 4.04 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.49 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 11408
1.22 KIPS
 
Image Classification (F16)
100% 11566
1.24 KIPS
 
Image Classification (I8)
81% 972
104.2 IPS
 
Image Segmentation (F32)
100% 4074
25.2 IPS
 
Image Segmentation (F16)
100% 4034
24.9 IPS
 
Image Segmentation (I8)
89% 1743
10.8 IPS
 
Pose Estimation (F32)
100% 40529
164.0 IPS
 
Pose Estimation (F16)
100% 40102
162.3 IPS
 
Pose Estimation (I8)
80% 304
1.23 IPS
 
Object Detection (F32)
100% 9457
331.9 IPS
 
Object Detection (F16)
100% 9252
324.7 IPS
 
Object Detection (I8)
52% 1373
48.2 IPS
 
Face Detection (F32)
100% 13055
150.0 IPS
 
Face Detection (F16)
100% 12981
149.1 IPS
 
Face Detection (I8)
75% 1404
16.1 IPS
 
Text Classification (F32)
100% 2285
903.9 IPS
 
Text Classification (F16)
100% 2294
907.2 IPS
 
Machine Translation (F32)
100% 3079
474.6 IPS
 
Machine Translation (F16)
100% 3087
475.8 IPS
 

Compare

Set Baseline Geekbench 6 now available