Geekbench ML Score

1065
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 26 2023 07:58 AM
Views 1

System Information

System Information
Operating System iOS 17.1.1
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,6
Motherboard J518AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.35 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1027
110.1 IPS
 
Image Classification (F16)
100% 1013
108.6 IPS
 
Image Classification (I8)
81% 400
42.8 IPS
 
Image Segmentation (F32)
100% 1374
8.49 IPS
 
Image Segmentation (F16)
100% 1366
8.44 IPS
 
Image Segmentation (I8)
89% 1564
9.66 IPS
 
Pose Estimation (F32)
100% 683
2.77 IPS
 
Pose Estimation (F16)
100% 682
2.76 IPS
 
Pose Estimation (I8)
80% 797
3.22 IPS
 
Object Detection (F32)
100% 1511
53.0 IPS
 
Object Detection (F16)
100% 1548
54.3 IPS
 
Object Detection (I8)
52% 601
21.1 IPS
 
Face Detection (F32)
100% 1774
20.4 IPS
 
Face Detection (F16)
100% 1759
20.2 IPS
 
Face Detection (I8)
75% 785
9.02 IPS
 
Text Classification (F32)
100% 879
347.7 IPS
 
Text Classification (F16)
100% 702
277.6 IPS
 
Machine Translation (F32)
100% 1869
288.1 IPS
 
Machine Translation (F16)
100% 1869
288.0 IPS
 

Compare

Set Baseline Geekbench 6 now available