User | benchmark_agent |
Upload Date | April 08 2025 05:13 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.7.4 (Build 23H420) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,9 |
Motherboard | Mac15,9 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.05 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1147
213.2 IPS |
|
Image Classification (HP)
|
100% |
7454
1.39 KIPS |
|
Image Classification (Q)
|
97% |
6910
1.29 KIPS |
|
Image Segmentation (SP)
|
100% |
841
13.6 IPS |
|
Image Segmentation (HP)
|
100% |
6433
104.3 IPS |
|
Image Segmentation (Q)
|
99% |
12703
205.9 IPS |
|
Pose Estimation (SP)
|
100% |
15343
17.9 IPS |
|
Pose Estimation (HP)
|
100% |
102757
119.9 IPS |
|
Pose Estimation (Q)
|
95% |
100105
117.3 IPS |
|
Object Detection (SP)
|
100% |
1184
94.0 IPS |
|
Object Detection (HP)
|
100% |
9522
755.3 IPS |
|
Object Detection (Q)
|
93% |
9545
761.6 IPS |
|
Face Detection (SP)
|
100% |
2326
27.6 IPS |
|
Face Detection (HP)
|
100% |
12764
151.7 IPS |
|
Face Detection (Q)
|
100% |
14800
175.9 IPS |
|
Depth Estimation (SP)
|
100% |
4062
31.3 IPS |
|
Depth Estimation (HP)
|
99% |
58652
451.9 IPS |
|
Depth Estimation (Q)
|
85% |
68293
533.9 IPS |
|
Style Transfer (SP)
|
100% |
15604
20.1 IPS |
|
Style Transfer (HP)
|
100% |
148274
190.6 IPS |
|
Style Transfer (Q)
|
96% |
140990
181.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3038
112.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
19279
711.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
23588
871.0 IPS |
|
Text Classification (SP)
|
100% |
757
1.01 KIPS |
|
Text Classification (HP)
|
100% |
3960
5.29 KIPS |
|
Text Classification (Q)
|
93% |
3872
5.20 KIPS |
|
Machine Translation (SP)
|
100% |
2023
34.8 IPS |
|
Machine Translation (HP)
|
100% |
2810
48.4 IPS |
|
Machine Translation (Q)
|
98% |
2813
48.6 IPS |