Geekbench ML Score

3481
Core ML CPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date May 08 2024 07:43 AM
Views 2

System Information

System Information
Operating System macOS 14.5 (Build 23F5074a)
Model MacBook Pro (16-inch, 2023)
Model IDMac14,6
Motherboard Mac14,6
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.66 GHz
Cluster 18 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 32.00 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1449
271.2 IPS
 
Image Classification (F16)
100% 1802
337.2 IPS
 
Image Classification (I8)
99% 1790
334.9 IPS
 
Image Segmentation (F32)
100% 919
15.3 IPS
 
Image Segmentation (F16)
100% 921
15.4 IPS
 
Image Segmentation (I8)
100% 924
15.4 IPS
 
Pose Estimation (F32)
100% 6113
7.40 IPS
 
Pose Estimation (F16)
100% 14332
17.4 IPS
 
Pose Estimation (I8)
100% 14233
17.2 IPS
 
Object Detection (F32)
100% 1486
110.9 IPS
 
Object Detection (F16)
100% 1978
147.6 IPS
 
Object Detection (I8)
97% 1490
111.2 IPS
 
Face Detection (F32)
100% 3034
36.1 IPS
 
Face Detection (F16)
97% 4400
52.3 IPS
 
Face Detection (I8)
97% 4378
52.1 IPS
 
Depth Estimation (F32)
100% 5523
42.8 IPS
 
Depth Estimation (F16)
100% 8551
66.3 IPS
 
Depth Estimation (I8)
99% 8555
66.3 IPS
 
Style Transfer (F32)
100% 16813
22.1 IPS
 
Style Transfer (F16)
100% 26210
34.5 IPS
 
Style Transfer (I8)
100% 26180
34.4 IPS
 
Image Super-Resolution (F32)
100% 3924
140.1 IPS
 
Image Super-Resolution (F16)
100% 4805
171.6 IPS
 
Image Super-Resolution (I8)
100% 4914
175.5 IPS
 
Text Classification (F32)
100% 2073
2.98 KIPS
 
Text Classification (F16)
100% 3011
4.33 KIPS
 
Text Classification (I8)
96% 3021
4.34 KIPS
 
Machine Translation (F32)
100% 1077
19.8 IPS
 
Machine Translation (F16)
100% 1588
29.2 IPS
 
Machine Translation (I8)
99% 1100
20.3 IPS
 

Compare

Set Baseline Geekbench 6 now available