Geekbench AI Score

5879
Single Precision Score
36322
Half Precision Score
49195
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

User rinsxi
Upload Date November 10 2024 05:28 AM
Views 7

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4 Max
System Information
Operating System macOS 15.1 (Build 24B2082)
Model Mac16,6
Model IDMac16,6
Motherboard Mac16,6
CPU Information
Name Apple M4 Max
Topology 1 Processor, 16 Cores
Identifier Apple M4 Max
Base Frequency 4.50 GHz
Cluster 112 Cores
Cluster 24 Cores
Memory Information
Size 48.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2127
395.5 IPS
 
Image Classification (HP)
100% 17144
3.19 KIPS
 
Image Classification (Q)
97% 22334
4.17 KIPS
 
Image Segmentation (SP)
100% 2523
40.9 IPS
 
Image Segmentation (HP)
100% 22545
365.5 IPS
 
Image Segmentation (Q)
99% 31116
504.4 IPS
 
Pose Estimation (SP)
100% 19064
22.2 IPS
 
Pose Estimation (HP)
100% 122866
143.4 IPS
 
Pose Estimation (Q)
95% 229969
269.5 IPS
 
Object Detection (SP)
100% 2516
199.5 IPS
 
Object Detection (HP)
100% 19561
1.55 KIPS
 
Object Detection (Q)
91% 23518
1.88 KIPS
 
Face Detection (SP)
100% 4636
55.1 IPS
 
Face Detection (HP)
100% 44142
524.5 IPS
 
Face Detection (Q)
100% 63904
759.3 IPS
 
Depth Estimation (SP)
100% 9026
69.5 IPS
 
Depth Estimation (HP)
99% 108676
837.3 IPS
 
Depth Estimation (Q)
85% 176284
1.38 KIPS
 
Style Transfer (SP)
100% 36791
47.3 IPS
 
Style Transfer (HP)
100% 231914
298.1 IPS
 
Style Transfer (Q)
96% 295480
381.3 IPS
 
Image Super-Resolution (SP)
100% 7180
265.1 IPS
 
Image Super-Resolution (HP)
100% 45839
1.69 KIPS
 
Image Super-Resolution (Q)
99% 77162
2.85 KIPS
 
Text Classification (SP)
100% 2957
3.95 KIPS
 
Text Classification (HP)
100% 5151
6.88 KIPS
 
Text Classification (Q)
93% 5231
7.02 KIPS
 
Machine Translation (SP)
100% 5870
101.1 IPS
 
Machine Translation (HP)
100% 16381
282.2 IPS
 
Machine Translation (Q)
98% 16442
284.1 IPS
 

Compare

Set Baseline Geekbench 6 now available