User | ESPD |
Upload Date | December 15 2024 05:25 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B2091) |
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 | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2066
384.2 IPS |
|
Image Classification (HP)
|
100% |
18157
3.38 KIPS |
|
Image Classification (Q)
|
97% |
22925
4.28 KIPS |
|
Image Segmentation (SP)
|
100% |
2472
40.1 IPS |
|
Image Segmentation (HP)
|
100% |
23385
379.1 IPS |
|
Image Segmentation (Q)
|
99% |
32974
534.5 IPS |
|
Pose Estimation (SP)
|
100% |
18869
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123629
144.3 IPS |
|
Pose Estimation (Q)
|
95% |
230469
270.1 IPS |
|
Object Detection (SP)
|
100% |
2465
195.5 IPS |
|
Object Detection (HP)
|
100% |
20505
1.63 KIPS |
|
Object Detection (Q)
|
91% |
25150
2.01 KIPS |
|
Face Detection (SP)
|
100% |
4513
53.6 IPS |
|
Face Detection (HP)
|
100% |
40116
476.7 IPS |
|
Face Detection (Q)
|
100% |
55592
660.6 IPS |
|
Depth Estimation (SP)
|
100% |
8806
67.8 IPS |
|
Depth Estimation (HP)
|
99% |
114162
879.6 IPS |
|
Depth Estimation (Q)
|
85% |
181650
1.42 KIPS |
|
Style Transfer (SP)
|
100% |
35318
45.4 IPS |
|
Style Transfer (HP)
|
100% |
239678
308.1 IPS |
|
Style Transfer (Q)
|
96% |
300761
388.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
7002
258.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
47218
1.74 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80120
2.96 KIPS |
|
Text Classification (SP)
|
100% |
2939
3.92 KIPS |
|
Text Classification (HP)
|
100% |
5560
7.42 KIPS |
|
Text Classification (Q)
|
93% |
5066
6.80 KIPS |
|
Machine Translation (SP)
|
100% |
5745
99.0 IPS |
|
Machine Translation (HP)
|
100% |
16594
285.8 IPS |
|
Machine Translation (Q)
|
98% |
16471
284.6 IPS |