User | Chineezze |
Upload Date | March 18 2025 02:32 PM |
Views | 14 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
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 | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2070
384.9 IPS |
|
Image Classification (HP)
|
100% |
16935
3.15 KIPS |
|
Image Classification (Q)
|
97% |
21449
4.00 KIPS |
|
Image Segmentation (SP)
|
100% |
2455
39.8 IPS |
|
Image Segmentation (HP)
|
100% |
23082
374.2 IPS |
|
Image Segmentation (Q)
|
99% |
32117
520.6 IPS |
|
Pose Estimation (SP)
|
100% |
18818
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123237
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
230526
270.2 IPS |
|
Object Detection (SP)
|
100% |
2484
197.0 IPS |
|
Object Detection (HP)
|
100% |
19409
1.54 KIPS |
|
Object Detection (Q)
|
91% |
22970
1.84 KIPS |
|
Face Detection (SP)
|
100% |
4586
54.5 IPS |
|
Face Detection (HP)
|
100% |
45281
538.0 IPS |
|
Face Detection (Q)
|
100% |
56320
669.2 IPS |
|
Depth Estimation (SP)
|
100% |
8648
66.6 IPS |
|
Depth Estimation (HP)
|
99% |
110889
854.3 IPS |
|
Depth Estimation (Q)
|
85% |
176114
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
35895
46.1 IPS |
|
Style Transfer (HP)
|
100% |
238329
306.4 IPS |
|
Style Transfer (Q)
|
96% |
304305
392.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
6996
258.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
45807
1.69 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77275
2.85 KIPS |
|
Text Classification (SP)
|
100% |
2944
3.93 KIPS |
|
Text Classification (HP)
|
100% |
5202
6.94 KIPS |
|
Text Classification (Q)
|
93% |
5248
7.04 KIPS |
|
Machine Translation (SP)
|
100% |
5762
99.2 IPS |
|
Machine Translation (HP)
|
100% |
16374
282.1 IPS |
|
Machine Translation (Q)
|
98% |
16064
277.6 IPS |