Geekbench ML Score

7774
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 28 2024 04:31 AM
Views 13
Notes MacBook Air (13-inch, M3, 2024)/M3/8Core CPU/8 Core GPU/8GB/256GBSSD

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model Mac15,12
Model IDMac15,12
Motherboard Mac15,12
CPU Information
Name Apple M3
Topology 1 Processor, 8 Cores
Identifier Apple M3
Base Frequency 4.05 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 8.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3727
697.5 IPS
 
Image Classification (F16)
100% 7200
1.35 KIPS
 
Image Classification (I8)
99% 7857
1.47 KIPS
 
Image Segmentation (F32)
100% 1690
28.2 IPS
 
Image Segmentation (F16)
100% 2138
35.7 IPS
 
Image Segmentation (I8)
100% 2118
35.4 IPS
 
Pose Estimation (F32)
100% 19239
23.3 IPS
 
Pose Estimation (F16)
100% 96344
116.7 IPS
 
Pose Estimation (I8)
100% 98851
119.7 IPS
 
Object Detection (F32)
100% 2551
190.5 IPS
 
Object Detection (F16)
100% 5621
419.6 IPS
 
Object Detection (I8)
97% 2770
206.8 IPS
 
Face Detection (F32)
100% 9875
117.4 IPS
 
Face Detection (F16)
97% 12821
152.4 IPS
 
Face Detection (I8)
96% 12847
152.8 IPS
 
Depth Estimation (F32)
100% 14941
115.9 IPS
 
Depth Estimation (F16)
100% 44625
346.1 IPS
 
Depth Estimation (I8)
37% 40660
315.3 IPS
 
Style Transfer (F32)
100% 43193
56.8 IPS
 
Style Transfer (F16)
100% 148290
195.1 IPS
 
Style Transfer (I8)
100% 148916
195.9 IPS
 
Image Super-Resolution (F32)
100% 6159
220.0 IPS
 
Image Super-Resolution (F16)
100% 19252
687.6 IPS
 
Image Super-Resolution (I8)
100% 20319
725.6 IPS
 
Text Classification (F32)
100% 610
876.3 IPS
 
Text Classification (F16)
100% 697
1.00 KIPS
 
Text Classification (I8)
96% 694
997.8 IPS
 
Machine Translation (F32)
100% 696
12.8 IPS
 
Machine Translation (F16)
100% 3144
57.9 IPS
 
Machine Translation (I8)
99% 684
12.6 IPS
 

Compare

Set Baseline Geekbench 6 now available