Geekbench AI Score

14388
Single Precision Score
16167
Half Precision Score
14354
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User Coin1news
Upload Date December 10 2024 07:42 AM
Views 2

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M4 Pro
System Information
Operating System macOS 15.1.1 (Build 24B2091)
Model Mac mini (2024)
Model IDMac16,11
Motherboard Mac16,11
CPU Information
Name Apple M4 Pro
Topology 1 Processor, 14 Cores
Identifier Apple M4 Pro
Base Frequency 4.50 GHz
Cluster 110 Cores
Cluster 24 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 7814
1.45 KIPS
 
Image Classification (HP)
100% 8376
1.56 KIPS
 
Image Classification (Q)
97% 7098
1.32 KIPS
 
Image Segmentation (SP)
100% 11983
194.3 IPS
 
Image Segmentation (HP)
100% 13128
212.8 IPS
 
Image Segmentation (Q)
99% 13272
215.2 IPS
 
Pose Estimation (SP)
100% 56868
66.4 IPS
 
Pose Estimation (HP)
100% 59362
69.3 IPS
 
Pose Estimation (Q)
95% 56141
65.8 IPS
 
Object Detection (SP)
100% 7210
571.9 IPS
 
Object Detection (HP)
100% 7729
613.0 IPS
 
Object Detection (Q)
91% 6436
514.3 IPS
 
Face Detection (SP)
100% 25642
304.7 IPS
 
Face Detection (HP)
100% 27068
321.6 IPS
 
Face Detection (Q)
100% 20796
247.1 IPS
 
Depth Estimation (SP)
100% 33174
255.6 IPS
 
Depth Estimation (HP)
99% 35726
275.2 IPS
 
Depth Estimation (Q)
85% 29252
228.6 IPS
 
Style Transfer (SP)
100% 123640
158.9 IPS
 
Style Transfer (HP)
100% 134498
172.9 IPS
 
Style Transfer (Q)
96% 127338
164.3 IPS
 
Image Super-Resolution (SP)
100% 23071
851.9 IPS
 
Image Super-Resolution (HP)
100% 24382
900.3 IPS
 
Image Super-Resolution (Q)
99% 19764
729.8 IPS
 
Text Classification (SP)
100% 2930
3.91 KIPS
 
Text Classification (HP)
100% 5225
6.97 KIPS
 
Text Classification (Q)
93% 5121
6.87 KIPS
 
Machine Translation (SP)
100% 1393
24.0 IPS
 
Machine Translation (HP)
100% 1460
25.2 IPS
 
Machine Translation (Q)
98% 1392
24.1 IPS
 

Compare

Set Baseline Geekbench 6 now available