Geekbench ML Score

8392
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 28 2024 04:23 AM
Views 24
Notes MacBook Air (15-inch, M3, 2024)/M3/8Core CPU/10 Core GPU/8GB/256GBSSD

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model Mac15,13
Model IDMac15,13
Motherboard Mac15,13
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% 4132
773.1 IPS
 
Image Classification (F16)
100% 7397
1.38 KIPS
 
Image Classification (I8)
99% 7894
1.48 KIPS
 
Image Segmentation (F32)
100% 1786
29.8 IPS
 
Image Segmentation (F16)
100% 2118
35.4 IPS
 
Image Segmentation (I8)
100% 2075
34.7 IPS
 
Pose Estimation (F32)
100% 23828
28.9 IPS
 
Pose Estimation (F16)
100% 97423
118.0 IPS
 
Pose Estimation (I8)
100% 98315
119.1 IPS
 
Object Detection (F32)
100% 3278
244.7 IPS
 
Object Detection (F16)
100% 5507
411.1 IPS
 
Object Detection (I8)
97% 2799
209.0 IPS
 
Face Detection (F32)
100% 10549
125.4 IPS
 
Face Detection (F16)
97% 12799
152.2 IPS
 
Face Detection (I8)
96% 12900
153.4 IPS
 
Depth Estimation (F32)
100% 15918
123.4 IPS
 
Depth Estimation (F16)
100% 42511
329.7 IPS
 
Depth Estimation (I8)
37% 46206
358.3 IPS
 
Style Transfer (F32)
100% 49219
64.7 IPS
 
Style Transfer (F16)
100% 147994
194.7 IPS
 
Style Transfer (I8)
100% 147764
194.4 IPS
 
Image Super-Resolution (F32)
100% 10225
365.2 IPS
 
Image Super-Resolution (F16)
100% 17186
613.8 IPS
 
Image Super-Resolution (I8)
100% 19805
707.3 IPS
 
Text Classification (F32)
100% 1388
1.99 KIPS
 
Text Classification (F16)
100% 724
1.04 KIPS
 
Text Classification (I8)
96% 723
1.04 KIPS
 
Machine Translation (F32)
100% 711
13.1 IPS
 
Machine Translation (F16)
100% 3371
62.0 IPS
 
Machine Translation (I8)
99% 671
12.3 IPS
 

Compare

Set Baseline Geekbench 6 now available