Geekbench ML Score

7277
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date August 16 2024 05:40 PM
Views 1

System Information

System Information
Operating System macOS 14.6.1 (Build 23G93)
Model Mac mini (2023)
Model IDMac14,3
Motherboard Mac14,3
CPU Information
Name Apple M2
Topology 1 Processor, 8 Cores
Identifier Apple M2
Base Frequency 3.48 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 16.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3398
635.8 IPS
 
Image Classification (F16)
100% 6823
1.28 KIPS
 
Image Classification (I8)
99% 7223
1.35 KIPS
 
Image Segmentation (F32)
100% 1454
24.3 IPS
 
Image Segmentation (F16)
100% 1588
26.5 IPS
 
Image Segmentation (I8)
100% 1619
27.0 IPS
 
Pose Estimation (F32)
100% 22959
27.8 IPS
 
Pose Estimation (F16)
100% 82330
99.7 IPS
 
Pose Estimation (I8)
100% 84285
102.1 IPS
 
Object Detection (F32)
100% 2910
217.2 IPS
 
Object Detection (F16)
100% 4516
337.1 IPS
 
Object Detection (I8)
97% 2697
201.4 IPS
 
Face Detection (F32)
100% 9361
111.3 IPS
 
Face Detection (F16)
97% 10758
127.9 IPS
 
Face Detection (I8)
96% 10713
127.4 IPS
 
Depth Estimation (F32)
100% 16246
126.0 IPS
 
Depth Estimation (F16)
100% 36532
283.3 IPS
 
Depth Estimation (I8)
37% 37198
288.5 IPS
 
Style Transfer (F32)
100% 40610
53.4 IPS
 
Style Transfer (F16)
100% 135471
178.2 IPS
 
Style Transfer (I8)
100% 135048
177.6 IPS
 
Image Super-Resolution (F32)
100% 8818
314.9 IPS
 
Image Super-Resolution (F16)
100% 18773
670.4 IPS
 
Image Super-Resolution (I8)
100% 18749
669.6 IPS
 
Text Classification (F32)
100% 472
679.1 IPS
 
Text Classification (F16)
100% 565
811.6 IPS
 
Text Classification (I8)
96% 586
841.6 IPS
 
Machine Translation (F32)
100% 952
17.5 IPS
 
Machine Translation (F16)
100% 2847
52.4 IPS
 
Machine Translation (I8)
99% 879
16.2 IPS
 

Compare

Set Baseline Geekbench 6 now available