User | tntoak |
Upload Date | March 26 2025 06:16 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2083
387.4 IPS |
|
Image Classification (HP)
|
100% |
17331
3.22 KIPS |
|
Image Classification (Q)
|
97% |
21765
4.06 KIPS |
|
Image Segmentation (SP)
|
100% |
2438
39.5 IPS |
|
Image Segmentation (HP)
|
100% |
23144
375.2 IPS |
|
Image Segmentation (Q)
|
99% |
31912
517.3 IPS |
|
Pose Estimation (SP)
|
100% |
18808
21.9 IPS |
|
Pose Estimation (HP)
|
100% |
123270
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
231194
271.0 IPS |
|
Object Detection (SP)
|
100% |
2482
196.9 IPS |
|
Object Detection (HP)
|
100% |
19712
1.56 KIPS |
|
Object Detection (Q)
|
91% |
23495
1.88 KIPS |
|
Face Detection (SP)
|
100% |
4631
55.0 IPS |
|
Face Detection (HP)
|
100% |
45456
540.1 IPS |
|
Face Detection (Q)
|
100% |
65640
779.9 IPS |
|
Depth Estimation (SP)
|
100% |
8836
68.1 IPS |
|
Depth Estimation (HP)
|
99% |
105652
814.0 IPS |
|
Depth Estimation (Q)
|
85% |
177735
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
35664
45.8 IPS |
|
Style Transfer (HP)
|
100% |
239063
307.3 IPS |
|
Style Transfer (Q)
|
96% |
302094
389.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
7014
259.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
46898
1.73 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76304
2.82 KIPS |
|
Text Classification (SP)
|
100% |
2928
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5152
6.88 KIPS |
|
Text Classification (Q)
|
93% |
5360
7.19 KIPS |
|
Machine Translation (SP)
|
100% |
5680
97.8 IPS |
|
Machine Translation (HP)
|
100% |
16348
281.6 IPS |
|
Machine Translation (Q)
|
98% |
16348
282.5 IPS |