User | ddalledo |
Upload Date | January 22 2025 12:32 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2073
385.5 IPS |
|
Image Classification (HP)
|
100% |
17466
3.25 KIPS |
|
Image Classification (Q)
|
97% |
22024
4.11 KIPS |
|
Image Segmentation (SP)
|
100% |
2470
40.0 IPS |
|
Image Segmentation (HP)
|
100% |
23149
375.3 IPS |
|
Image Segmentation (Q)
|
99% |
32601
528.5 IPS |
|
Pose Estimation (SP)
|
100% |
18818
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123918
144.6 IPS |
|
Pose Estimation (Q)
|
95% |
234328
274.6 IPS |
|
Object Detection (SP)
|
100% |
2471
196.0 IPS |
|
Object Detection (HP)
|
100% |
20639
1.64 KIPS |
|
Object Detection (Q)
|
91% |
25221
2.02 KIPS |
|
Face Detection (SP)
|
100% |
4532
53.9 IPS |
|
Face Detection (HP)
|
100% |
45059
535.4 IPS |
|
Face Detection (Q)
|
100% |
61421
729.8 IPS |
|
Depth Estimation (SP)
|
100% |
8789
67.7 IPS |
|
Depth Estimation (HP)
|
99% |
113969
878.1 IPS |
|
Depth Estimation (Q)
|
85% |
183150
1.43 KIPS |
|
Style Transfer (SP)
|
100% |
35860
46.1 IPS |
|
Style Transfer (HP)
|
100% |
238119
306.1 IPS |
|
Style Transfer (Q)
|
96% |
305702
394.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
7125
263.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
46289
1.71 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79605
2.94 KIPS |
|
Text Classification (SP)
|
100% |
2932
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5214
6.96 KIPS |
|
Text Classification (Q)
|
93% |
5090
6.83 KIPS |
|
Machine Translation (SP)
|
100% |
5755
99.1 IPS |
|
Machine Translation (HP)
|
100% |
16299
280.8 IPS |
|
Machine Translation (Q)
|
98% |
16939
292.7 IPS |