User | joostl |
Upload Date | February 07 2025 02:13 PM |
Views | 12 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2087
388.2 IPS |
|
Image Classification (HP)
|
100% |
17817
3.31 KIPS |
|
Image Classification (Q)
|
97% |
22727
4.24 KIPS |
|
Image Segmentation (SP)
|
100% |
2503
40.6 IPS |
|
Image Segmentation (HP)
|
100% |
23326
378.1 IPS |
|
Image Segmentation (Q)
|
99% |
32247
522.7 IPS |
|
Pose Estimation (SP)
|
100% |
18967
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
123580
144.2 IPS |
|
Pose Estimation (Q)
|
95% |
231586
271.4 IPS |
|
Object Detection (SP)
|
100% |
2498
198.1 IPS |
|
Object Detection (HP)
|
100% |
19585
1.55 KIPS |
|
Object Detection (Q)
|
91% |
24299
1.94 KIPS |
|
Face Detection (SP)
|
100% |
4590
54.5 IPS |
|
Face Detection (HP)
|
100% |
44762
531.9 IPS |
|
Face Detection (Q)
|
100% |
63961
760.0 IPS |
|
Depth Estimation (SP)
|
100% |
8922
68.7 IPS |
|
Depth Estimation (HP)
|
99% |
109996
847.5 IPS |
|
Depth Estimation (Q)
|
85% |
177205
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
35336
45.4 IPS |
|
Style Transfer (HP)
|
100% |
238735
306.9 IPS |
|
Style Transfer (Q)
|
96% |
303897
392.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
7042
260.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
46417
1.71 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78874
2.91 KIPS |
|
Text Classification (SP)
|
100% |
2938
3.92 KIPS |
|
Text Classification (HP)
|
100% |
4770
6.37 KIPS |
|
Text Classification (Q)
|
93% |
5383
7.22 KIPS |
|
Machine Translation (SP)
|
100% |
5797
99.9 IPS |
|
Machine Translation (HP)
|
100% |
16139
278.0 IPS |
|
Machine Translation (Q)
|
98% |
17057
294.8 IPS |