Upload Date | October 09 2024 02:43 PM |
Views | 143 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A8332) |
Model | Mac16,1 |
Model ID | Mac16,1 |
Motherboard | Mac16,1 |
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% |
1983
368.8 IPS |
|
Image Classification (HP)
|
100% |
17890
3.33 KIPS |
|
Image Classification (Q)
|
97% |
26231
4.90 KIPS |
|
Image Segmentation (SP)
|
100% |
2194
35.6 IPS |
|
Image Segmentation (HP)
|
100% |
16329
264.7 IPS |
|
Image Segmentation (Q)
|
99% |
20357
330.0 IPS |
|
Pose Estimation (SP)
|
100% |
9854
11.5 IPS |
|
Pose Estimation (HP)
|
100% |
123353
143.9 IPS |
|
Pose Estimation (Q)
|
95% |
230281
269.9 IPS |
|
Object Detection (SP)
|
100% |
2267
179.8 IPS |
|
Object Detection (HP)
|
100% |
19081
1.51 KIPS |
|
Object Detection (Q)
|
91% |
27130
2.17 KIPS |
|
Face Detection (SP)
|
100% |
3851
45.8 IPS |
|
Face Detection (HP)
|
100% |
43027
511.3 IPS |
|
Face Detection (Q)
|
100% |
55618
660.9 IPS |
|
Depth Estimation (SP)
|
100% |
8294
63.9 IPS |
|
Depth Estimation (HP)
|
99% |
100661
775.5 IPS |
|
Depth Estimation (Q)
|
85% |
173491
1.36 KIPS |
|
Style Transfer (SP)
|
100% |
25143
32.3 IPS |
|
Style Transfer (HP)
|
100% |
233549
300.2 IPS |
|
Style Transfer (Q)
|
96% |
299002
385.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5820
214.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
51050
1.89 KIPS |
|
Image Super-Resolution (Q)
|
99% |
88557
3.27 KIPS |
|
Text Classification (SP)
|
100% |
3063
4.09 KIPS |
|
Text Classification (HP)
|
100% |
6452
8.61 KIPS |
|
Text Classification (Q)
|
93% |
6490
8.71 KIPS |
|
Machine Translation (SP)
|
100% |
3907
67.3 IPS |
|
Machine Translation (HP)
|
100% |
16772
288.9 IPS |
|
Machine Translation (Q)
|
98% |
18660
322.5 IPS |