User | benchmark_agent |
Upload Date | April 08 2025 05:30 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
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 | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
8011
1.49 KIPS |
|
Image Classification (HP)
|
100% |
8341
1.55 KIPS |
|
Image Classification (Q)
|
97% |
7273
1.36 KIPS |
|
Image Segmentation (SP)
|
100% |
16837
272.9 IPS |
|
Image Segmentation (HP)
|
100% |
17535
284.2 IPS |
|
Image Segmentation (Q)
|
99% |
18060
292.8 IPS |
|
Pose Estimation (SP)
|
100% |
92036
107.4 IPS |
|
Pose Estimation (HP)
|
100% |
95392
111.3 IPS |
|
Pose Estimation (Q)
|
95% |
90294
105.8 IPS |
|
Object Detection (SP)
|
100% |
7970
632.1 IPS |
|
Object Detection (HP)
|
100% |
8443
669.7 IPS |
|
Object Detection (Q)
|
91% |
7150
571.3 IPS |
|
Face Detection (SP)
|
100% |
32006
380.3 IPS |
|
Face Detection (HP)
|
100% |
35496
421.8 IPS |
|
Face Detection (Q)
|
100% |
26838
318.9 IPS |
|
Depth Estimation (SP)
|
100% |
37925
292.2 IPS |
|
Depth Estimation (HP)
|
99% |
40778
314.2 IPS |
|
Depth Estimation (Q)
|
85% |
34771
271.7 IPS |
|
Style Transfer (SP)
|
100% |
185942
239.0 IPS |
|
Style Transfer (HP)
|
100% |
204772
263.2 IPS |
|
Style Transfer (Q)
|
96% |
195643
252.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
25362
936.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
26087
963.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
21434
791.5 IPS |
|
Text Classification (SP)
|
100% |
3093
4.13 KIPS |
|
Text Classification (HP)
|
100% |
5270
7.03 KIPS |
|
Text Classification (Q)
|
93% |
5294
7.11 KIPS |
|
Machine Translation (SP)
|
100% |
1150
19.8 IPS |
|
Machine Translation (HP)
|
100% |
1208
20.8 IPS |
|
Machine Translation (Q)
|
98% |
1210
20.9 IPS |