Geekbench AI Score

4693
Single Precision Score
37237
Half Precision Score
51558
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User jordan41902348
Upload Date February 06 2025 08:40 PM
Views 10

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4
System Information
Operating System macOS 15.3 (Build 24D60)
Model Mac mini (2024)
Model IDMac16,10
Motherboard Mac16,10
CPU Information
Name Apple M4
Topology 1 Processor, 10 Cores
Identifier Apple M4
Base Frequency 4.41 GHz
Cluster 14 Cores
Cluster 26 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2008
373.4 IPS
 
Image Classification (HP)
100% 18001
3.35 KIPS
 
Image Classification (Q)
97% 25446
4.75 KIPS
 
Image Segmentation (SP)
100% 2073
33.6 IPS
 
Image Segmentation (HP)
100% 22019
356.9 IPS
 
Image Segmentation (Q)
99% 30131
488.4 IPS
 
Pose Estimation (SP)
100% 9954
11.6 IPS
 
Pose Estimation (HP)
100% 124077
144.8 IPS
 
Pose Estimation (Q)
95% 232866
272.9 IPS
 
Object Detection (SP)
100% 2285
181.2 IPS
 
Object Detection (HP)
100% 18768
1.49 KIPS
 
Object Detection (Q)
91% 25849
2.07 KIPS
 
Face Detection (SP)
100% 3938
46.8 IPS
 
Face Detection (HP)
100% 43584
517.9 IPS
 
Face Detection (Q)
100% 59624
708.5 IPS
 
Depth Estimation (SP)
100% 8331
64.2 IPS
 
Depth Estimation (HP)
99% 99755
768.6 IPS
 
Depth Estimation (Q)
85% 169779
1.33 KIPS
 
Style Transfer (SP)
100% 25238
32.4 IPS
 
Style Transfer (HP)
100% 235799
303.1 IPS
 
Style Transfer (Q)
96% 300000
387.1 IPS
 
Image Super-Resolution (SP)
100% 5736
211.8 IPS
 
Image Super-Resolution (HP)
100% 49413
1.82 KIPS
 
Image Super-Resolution (Q)
99% 86215
3.18 KIPS
 
Text Classification (SP)
100% 2950
3.94 KIPS
 
Text Classification (HP)
100% 6823
9.11 KIPS
 
Text Classification (Q)
93% 6220
8.35 KIPS
 
Machine Translation (SP)
100% 3912
67.4 IPS
 
Machine Translation (HP)
100% 16070
276.8 IPS
 
Machine Translation (Q)
98% 17662
305.2 IPS
 

Compare

Set Baseline Geekbench 6 now available