User | edbond |
Upload Date | April 19 2025 05:52 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2059
383.0 IPS |
|
Image Classification (HP)
|
100% |
17982
3.34 KIPS |
|
Image Classification (Q)
|
97% |
23691
4.42 KIPS |
|
Image Segmentation (SP)
|
100% |
2303
37.3 IPS |
|
Image Segmentation (HP)
|
100% |
23381
379.0 IPS |
|
Image Segmentation (Q)
|
99% |
32623
528.8 IPS |
|
Pose Estimation (SP)
|
100% |
17107
20.0 IPS |
|
Pose Estimation (HP)
|
100% |
122644
143.1 IPS |
|
Pose Estimation (Q)
|
95% |
228332
267.6 IPS |
|
Object Detection (SP)
|
100% |
2468
195.7 IPS |
|
Object Detection (HP)
|
100% |
20519
1.63 KIPS |
|
Object Detection (Q)
|
91% |
24329
1.94 KIPS |
|
Face Detection (SP)
|
100% |
4669
55.5 IPS |
|
Face Detection (HP)
|
100% |
45545
541.2 IPS |
|
Face Detection (Q)
|
100% |
66259
787.3 IPS |
|
Depth Estimation (SP)
|
100% |
8650
66.6 IPS |
|
Depth Estimation (HP)
|
99% |
112329
865.4 IPS |
|
Depth Estimation (Q)
|
85% |
180048
1.41 KIPS |
|
Style Transfer (SP)
|
100% |
25546
32.8 IPS |
|
Style Transfer (HP)
|
100% |
238968
307.2 IPS |
|
Style Transfer (Q)
|
96% |
306465
395.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5959
220.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
46596
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
81686
3.02 KIPS |
|
Text Classification (SP)
|
100% |
2901
3.87 KIPS |
|
Text Classification (HP)
|
100% |
5877
7.84 KIPS |
|
Text Classification (Q)
|
93% |
6142
8.24 KIPS |
|
Machine Translation (SP)
|
100% |
5663
97.6 IPS |
|
Machine Translation (HP)
|
100% |
16448
283.3 IPS |
|
Machine Translation (Q)
|
98% |
16966
293.2 IPS |