User | benchmark_agent |
Upload Date | April 08 2025 05:57 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% |
1152
214.2 IPS |
|
Image Classification (HP)
|
100% |
7084
1.32 KIPS |
|
Image Classification (Q)
|
97% |
7664
1.43 KIPS |
|
Image Segmentation (SP)
|
100% |
840
13.6 IPS |
|
Image Segmentation (HP)
|
100% |
6386
103.5 IPS |
|
Image Segmentation (Q)
|
99% |
12713
206.1 IPS |
|
Pose Estimation (SP)
|
100% |
15164
17.7 IPS |
|
Pose Estimation (HP)
|
100% |
102684
119.8 IPS |
|
Pose Estimation (Q)
|
95% |
100045
117.3 IPS |
|
Object Detection (SP)
|
100% |
1253
99.4 IPS |
|
Object Detection (HP)
|
100% |
9273
735.5 IPS |
|
Object Detection (Q)
|
93% |
9655
770.4 IPS |
|
Face Detection (SP)
|
100% |
2309
27.4 IPS |
|
Face Detection (HP)
|
100% |
12569
149.3 IPS |
|
Face Detection (Q)
|
100% |
14960
177.8 IPS |
|
Depth Estimation (SP)
|
100% |
4124
31.8 IPS |
|
Depth Estimation (HP)
|
99% |
58409
450.0 IPS |
|
Depth Estimation (Q)
|
85% |
67982
531.5 IPS |
|
Style Transfer (SP)
|
100% |
15874
20.4 IPS |
|
Style Transfer (HP)
|
100% |
148980
191.5 IPS |
|
Style Transfer (Q)
|
96% |
140199
180.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3427
126.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
19010
701.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
23154
855.0 IPS |
|
Text Classification (SP)
|
100% |
553
738.0 IPS |
|
Text Classification (HP)
|
100% |
3935
5.25 KIPS |
|
Text Classification (Q)
|
93% |
4015
5.39 KIPS |
|
Machine Translation (SP)
|
100% |
2104
36.2 IPS |
|
Machine Translation (HP)
|
100% |
2812
48.4 IPS |
|
Machine Translation (Q)
|
98% |
2806
48.5 IPS |