Geekbench ML Score

2783
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 13 2023 06:15 PM
Views 26

System Information

System Information
Operating System iOS 17.0
Model iPhone16,1
Model IDiPhone16,1
Motherboard D83AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.78 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.50 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2914
312.3 IPS
 
Image Classification (F16)
100% 4911
526.1 IPS
 
Image Classification (I8)
81% 836
89.6 IPS
 
Image Segmentation (F32)
100% 6091
37.6 IPS
 
Image Segmentation (F16)
100% 9868
61.0 IPS
 
Image Segmentation (I8)
89% 1489
9.20 IPS
 
Pose Estimation (F32)
100% 2490
10.1 IPS
 
Pose Estimation (F16)
100% 5297
21.4 IPS
 
Pose Estimation (I8)
80% 278
1.12 IPS
 
Object Detection (F32)
100% 3826
134.3 IPS
 
Object Detection (F16)
100% 5035
176.7 IPS
 
Object Detection (I8)
52% 1185
41.6 IPS
 
Face Detection (F32)
100% 6048
69.5 IPS
 
Face Detection (F16)
97% 11087
127.4 IPS
 
Face Detection (I8)
75% 1142
13.1 IPS
 
Text Classification (F32)
100% 2374
938.9 IPS
 
Text Classification (F16)
100% 2122
839.2 IPS
 
Machine Translation (F32)
100% 2832
436.5 IPS
 
Machine Translation (F16)
100% 2862
441.2 IPS
 

Compare

Set Baseline Geekbench 6 now available