Geekbench ML Score

1374
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 25 2024 12:17 PM
Views 1

System Information

System Information
Operating System iOS 15.6.1
Model iPad Air (3rd generation)
Model IDiPad11,3
Motherboard J217AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 2.84 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3780
405.0 IPS
 
Image Classification (F16)
100% 3681
394.4 IPS
 
Image Classification (I8)
81% 402
43.1 IPS
 
Image Segmentation (F32)
100% 1382
8.53 IPS
 
Image Segmentation (F16)
100% 1411
8.71 IPS
 
Image Segmentation (I8)
89% 746
4.60 IPS
 
Pose Estimation (F32)
100% 7258
29.4 IPS
 
Pose Estimation (F16)
100% 7434
30.1 IPS
 
Pose Estimation (I8)
80% 142
0.57 IPS
 
Object Detection (F32)
94% 3986
139.9 IPS
 
Object Detection (F16)
94% 4011
140.8 IPS
 
Object Detection (I8)
52% 565
19.8 IPS
 
Face Detection (F32)
67% 3738
42.9 IPS
 
Face Detection (F16)
67% 3775
43.4 IPS
 
Face Detection (I8)
75% 549
6.31 IPS
 
Text Classification (F32)
100% 317
125.2 IPS
 
Text Classification (F16)
100% 311
123.2 IPS
 
Machine Translation (F32)
100% 990
152.6 IPS
 
Machine Translation (F16)
100% 991
152.8 IPS
 

Compare

Set Baseline Geekbench 6 now available