User | ankur_mandal |
Upload Date | May 03 2025 05:54 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | Mac16,12 |
Model ID | Mac16,12 |
Motherboard | Mac16,12 |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M4 |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4421
822.2 IPS |
|
Image Classification (HP)
|
100% |
4837
899.6 IPS |
|
Image Classification (Q)
|
96% |
4465
833.8 IPS |
|
Image Segmentation (SP)
|
100% |
7138
115.7 IPS |
|
Image Segmentation (HP)
|
100% |
7767
125.9 IPS |
|
Image Segmentation (Q)
|
99% |
7581
122.9 IPS |
|
Pose Estimation (SP)
|
100% |
27787
32.4 IPS |
|
Pose Estimation (HP)
|
100% |
29941
34.9 IPS |
|
Pose Estimation (Q)
|
96% |
29023
34.0 IPS |
|
Object Detection (SP)
|
100% |
4610
365.7 IPS |
|
Object Detection (HP)
|
100% |
5245
416.0 IPS |
|
Object Detection (Q)
|
92% |
4742
378.5 IPS |
|
Face Detection (SP)
|
100% |
12197
144.9 IPS |
|
Face Detection (HP)
|
100% |
16037
190.6 IPS |
|
Face Detection (Q)
|
100% |
13131
156.0 IPS |
|
Depth Estimation (SP)
|
100% |
20775
160.1 IPS |
|
Depth Estimation (HP)
|
99% |
22576
173.9 IPS |
|
Depth Estimation (Q)
|
85% |
20498
160.3 IPS |
|
Style Transfer (SP)
|
100% |
56014
72.0 IPS |
|
Style Transfer (HP)
|
100% |
67189
86.4 IPS |
|
Style Transfer (Q)
|
96% |
65300
84.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
11742
433.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
12562
463.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
11126
410.8 IPS |
|
Text Classification (SP)
|
100% |
2948
3.93 KIPS |
|
Text Classification (HP)
|
100% |
5398
7.20 KIPS |
|
Text Classification (Q)
|
93% |
5562
7.46 KIPS |
|
Machine Translation (SP)
|
100% |
1480
25.5 IPS |
|
Machine Translation (HP)
|
100% |
1623
28.0 IPS |
|
Machine Translation (Q)
|
98% |
1584
27.4 IPS |