Geekbench ML Score

3449
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 15 2024 12:26 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 GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3688
395.1 IPS
 
Image Classification (F16)
100% 7493
802.9 IPS
 
Image Classification (I8)
81% 976
104.6 IPS
 
Image Segmentation (F32)
100% 8131
50.2 IPS
 
Image Segmentation (F16)
100% 13253
81.9 IPS
 
Image Segmentation (I8)
89% 1771
10.9 IPS
 
Pose Estimation (F32)
100% 2291
9.27 IPS
 
Pose Estimation (F16)
100% 6658
26.9 IPS
 
Pose Estimation (I8)
80% 302
1.22 IPS
 
Object Detection (F32)
100% 4537
159.2 IPS
 
Object Detection (F16)
100% 6213
218.0 IPS
 
Object Detection (I8)
52% 1371
48.1 IPS
 
Face Detection (F32)
100% 6955
79.9 IPS
 
Face Detection (F16)
97% 14269
163.9 IPS
 
Face Detection (I8)
75% 1388
15.9 IPS
 
Text Classification (F32)
100% 3780
1.49 KIPS
 
Text Classification (F16)
100% 3633
1.44 KIPS
 
Machine Translation (F32)
100% 3078
474.4 IPS
 
Machine Translation (F16)
100% 3085
475.5 IPS
 

Compare

Set Baseline Geekbench 6 now available