User | daveporter |
Upload Date | July 18 2025 08:16 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | Mac mini (2024) |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
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 | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2069
384.7 IPS |
|
Image Classification (HP)
|
100% |
3134
582.8 IPS |
|
Image Classification (Q)
|
96% |
2215
413.7 IPS |
|
Image Segmentation (SP)
|
100% |
2411
39.1 IPS |
|
Image Segmentation (HP)
|
100% |
3649
59.1 IPS |
|
Image Segmentation (Q)
|
99% |
3989
64.7 IPS |
|
Pose Estimation (SP)
|
100% |
17274
20.2 IPS |
|
Pose Estimation (HP)
|
100% |
31224
36.4 IPS |
|
Pose Estimation (Q)
|
95% |
24069
28.2 IPS |
|
Object Detection (SP)
|
100% |
2429
192.7 IPS |
|
Object Detection (HP)
|
97% |
3760
299.3 IPS |
|
Object Detection (Q)
|
94% |
2742
218.6 IPS |
|
Face Detection (SP)
|
100% |
4648
55.2 IPS |
|
Face Detection (HP)
|
100% |
8009
95.2 IPS |
|
Face Detection (Q)
|
100% |
4654
55.3 IPS |
|
Depth Estimation (SP)
|
100% |
8601
66.3 IPS |
|
Depth Estimation (HP)
|
97% |
14452
111.7 IPS |
|
Depth Estimation (Q)
|
86% |
10236
79.9 IPS |
|
Style Transfer (SP)
|
100% |
26424
34.0 IPS |
|
Style Transfer (HP)
|
100% |
51180
65.8 IPS |
|
Style Transfer (Q)
|
96% |
39801
51.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
6102
225.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
10266
379.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
5917
218.5 IPS |
|
Text Classification (SP)
|
100% |
2916
3.89 KIPS |
|
Text Classification (HP)
|
100% |
5337
7.12 KIPS |
|
Text Classification (Q)
|
93% |
5327
7.15 KIPS |
|
Machine Translation (SP)
|
100% |
5761
99.2 IPS |
|
Machine Translation (HP)
|
98% |
9307
160.8 IPS |
|
Machine Translation (Q)
|
98% |
9312
160.9 IPS |