User | RG22032 |
Upload Date | September 06 2025 12:05 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
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% |
2073
385.4 IPS |
|
Image Classification (HP)
|
100% |
17866
3.32 KIPS |
|
Image Classification (Q)
|
97% |
23260
4.34 KIPS |
|
Image Segmentation (SP)
|
100% |
2284
37.0 IPS |
|
Image Segmentation (HP)
|
100% |
23364
378.7 IPS |
|
Image Segmentation (Q)
|
99% |
32923
533.7 IPS |
|
Pose Estimation (SP)
|
100% |
17231
20.1 IPS |
|
Pose Estimation (HP)
|
100% |
122603
143.1 IPS |
|
Pose Estimation (Q)
|
95% |
230210
269.8 IPS |
|
Object Detection (SP)
|
100% |
2491
197.6 IPS |
|
Object Detection (HP)
|
100% |
19968
1.58 KIPS |
|
Object Detection (Q)
|
91% |
24167
1.93 KIPS |
|
Face Detection (SP)
|
100% |
4674
55.5 IPS |
|
Face Detection (HP)
|
100% |
46150
548.4 IPS |
|
Face Detection (Q)
|
100% |
66740
793.0 IPS |
|
Depth Estimation (SP)
|
100% |
8620
66.4 IPS |
|
Depth Estimation (HP)
|
99% |
108860
838.7 IPS |
|
Depth Estimation (Q)
|
85% |
178377
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
25601
32.9 IPS |
|
Style Transfer (HP)
|
100% |
237668
305.5 IPS |
|
Style Transfer (Q)
|
96% |
301847
389.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5964
220.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
47574
1.76 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82185
3.03 KIPS |
|
Text Classification (SP)
|
100% |
2896
3.86 KIPS |
|
Text Classification (HP)
|
100% |
5975
7.97 KIPS |
|
Text Classification (Q)
|
93% |
5784
7.76 KIPS |
|
Machine Translation (SP)
|
100% |
5703
98.2 IPS |
|
Machine Translation (HP)
|
100% |
16592
285.8 IPS |
|
Machine Translation (Q)
|
98% |
16654
287.8 IPS |