Geekbench ML Score

1386
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 05 2023 12:50 AM
Views 1

System Information

System Information
Operating System iOS 17.0.3
Model iPhone 11 Pro Max
Model IDiPhone12,5
Motherboard D431AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.66 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1434
153.6 IPS
 
Image Classification (F16)
100% 1548
165.8 IPS
 
Image Classification (I8)
81% 450
48.2 IPS
 
Image Segmentation (F32)
100% 3328
20.6 IPS
 
Image Segmentation (F16)
100% 5546
34.3 IPS
 
Image Segmentation (I8)
89% 815
5.03 IPS
 
Pose Estimation (F32)
100% 1481
5.99 IPS
 
Pose Estimation (F16)
100% 4385
17.7 IPS
 
Pose Estimation (I8)
80% 154
0.62 IPS
 
Object Detection (F32)
100% 1458
51.2 IPS
 
Object Detection (F16)
99% 1806
63.4 IPS
 
Object Detection (I8)
52% 633
22.2 IPS
 
Face Detection (F32)
100% 3582
41.2 IPS
 
Face Detection (F16)
97% 5366
61.6 IPS
 
Face Detection (I8)
75% 631
7.25 IPS
 
Text Classification (F32)
100% 945
373.6 IPS
 
Text Classification (F16)
98% 1204
476.2 IPS
 
Machine Translation (F32)
100% 1199
184.9 IPS
 
Machine Translation (F16)
100% 1206
185.9 IPS
 

Compare

Set Baseline Geekbench 6 now available