User | WeisseMoehre |
Upload Date | May 24 2025 07:03 AM |
Views | 11 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.50 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2126
395.3 IPS |
|
Image Classification (HP)
|
100% |
17835
3.32 KIPS |
|
Image Classification (Q)
|
97% |
22998
4.29 KIPS |
|
Image Segmentation (SP)
|
100% |
2422
39.3 IPS |
|
Image Segmentation (HP)
|
100% |
22630
366.8 IPS |
|
Image Segmentation (Q)
|
99% |
31182
505.5 IPS |
|
Pose Estimation (SP)
|
100% |
18121
21.1 IPS |
|
Pose Estimation (HP)
|
100% |
122490
142.9 IPS |
|
Pose Estimation (Q)
|
95% |
228224
267.5 IPS |
|
Object Detection (SP)
|
100% |
2634
209.0 IPS |
|
Object Detection (HP)
|
100% |
19368
1.54 KIPS |
|
Object Detection (Q)
|
91% |
23441
1.87 KIPS |
|
Face Detection (SP)
|
100% |
4948
58.8 IPS |
|
Face Detection (HP)
|
100% |
45424
539.7 IPS |
|
Face Detection (Q)
|
100% |
57898
688.0 IPS |
|
Depth Estimation (SP)
|
100% |
8829
68.0 IPS |
|
Depth Estimation (HP)
|
99% |
113555
874.9 IPS |
|
Depth Estimation (Q)
|
85% |
179988
1.41 KIPS |
|
Style Transfer (SP)
|
100% |
26449
34.0 IPS |
|
Style Transfer (HP)
|
100% |
232125
298.4 IPS |
|
Style Transfer (Q)
|
96% |
298052
384.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
6093
225.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
45735
1.69 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77747
2.87 KIPS |
|
Text Classification (SP)
|
100% |
2938
3.92 KIPS |
|
Text Classification (HP)
|
100% |
6274
8.37 KIPS |
|
Text Classification (Q)
|
93% |
5797
7.78 KIPS |
|
Machine Translation (SP)
|
100% |
6090
104.9 IPS |
|
Machine Translation (HP)
|
100% |
16511
284.4 IPS |
|
Machine Translation (Q)
|
98% |
16532
285.7 IPS |