Upload Date | September 14 2025 12:18 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A353) |
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 | 4.42 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2043
380.0 IPS |
|
Image Classification (HP)
|
100% |
18818
3.50 KIPS |
|
Image Classification (Q)
|
97% |
27320
5.10 KIPS |
|
Image Segmentation (SP)
|
100% |
2116
34.3 IPS |
|
Image Segmentation (HP)
|
100% |
22600
366.4 IPS |
|
Image Segmentation (Q)
|
99% |
31297
507.3 IPS |
|
Pose Estimation (SP)
|
100% |
9910
11.6 IPS |
|
Pose Estimation (HP)
|
100% |
122642
143.1 IPS |
|
Pose Estimation (Q)
|
95% |
232498
272.5 IPS |
|
Object Detection (SP)
|
100% |
2394
189.9 IPS |
|
Object Detection (HP)
|
100% |
19612
1.56 KIPS |
|
Object Detection (Q)
|
91% |
27229
2.18 KIPS |
|
Face Detection (SP)
|
100% |
3340
39.7 IPS |
|
Face Detection (HP)
|
100% |
41725
495.8 IPS |
|
Face Detection (Q)
|
100% |
60536
719.3 IPS |
|
Depth Estimation (SP)
|
100% |
7166
55.2 IPS |
|
Depth Estimation (HP)
|
99% |
94458
727.7 IPS |
|
Depth Estimation (Q)
|
85% |
160342
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
15833
20.4 IPS |
|
Style Transfer (HP)
|
100% |
229121
294.5 IPS |
|
Style Transfer (Q)
|
96% |
314129
405.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4860
179.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
54186
2.00 KIPS |
|
Image Super-Resolution (Q)
|
99% |
88485
3.27 KIPS |
|
Text Classification (SP)
|
100% |
3370
4.50 KIPS |
|
Text Classification (HP)
|
99% |
5835
7.79 KIPS |
|
Text Classification (Q)
|
93% |
5806
7.79 KIPS |
|
Machine Translation (SP)
|
100% |
4428
76.3 IPS |
|
Machine Translation (HP)
|
100% |
17010
293.0 IPS |
|
Machine Translation (Q)
|
98% |
18985
328.1 IPS |