User | peterb123 |
Upload Date | September 20 2025 03:22 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A354) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,7 |
Motherboard | Mac16,7 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2165
402.7 IPS |
|
Image Classification (HP)
|
100% |
17547
3.26 KIPS |
|
Image Classification (Q)
|
97% |
21709
4.05 KIPS |
|
Image Segmentation (SP)
|
100% |
2296
37.2 IPS |
|
Image Segmentation (HP)
|
100% |
23903
387.5 IPS |
|
Image Segmentation (Q)
|
99% |
31850
516.3 IPS |
|
Pose Estimation (SP)
|
100% |
17210
20.1 IPS |
|
Pose Estimation (HP)
|
100% |
122409
142.8 IPS |
|
Pose Estimation (Q)
|
95% |
230929
270.7 IPS |
|
Object Detection (SP)
|
100% |
2575
204.3 IPS |
|
Object Detection (HP)
|
100% |
20449
1.62 KIPS |
|
Object Detection (Q)
|
91% |
24351
1.95 KIPS |
|
Face Detection (SP)
|
100% |
4936
58.7 IPS |
|
Face Detection (HP)
|
100% |
44704
531.2 IPS |
|
Face Detection (Q)
|
100% |
63339
752.6 IPS |
|
Depth Estimation (SP)
|
100% |
8787
67.7 IPS |
|
Depth Estimation (HP)
|
99% |
105478
812.6 IPS |
|
Depth Estimation (Q)
|
85% |
177673
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
30562
39.3 IPS |
|
Style Transfer (HP)
|
100% |
237949
305.9 IPS |
|
Style Transfer (Q)
|
96% |
329267
424.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
7107
262.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
49312
1.82 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79114
2.92 KIPS |
|
Text Classification (SP)
|
100% |
3226
4.31 KIPS |
|
Text Classification (HP)
|
99% |
5768
7.70 KIPS |
|
Text Classification (Q)
|
93% |
5564
7.47 KIPS |
|
Machine Translation (SP)
|
100% |
5985
103.1 IPS |
|
Machine Translation (HP)
|
100% |
17105
294.6 IPS |
|
Machine Translation (Q)
|
98% |
16611
287.1 IPS |