User | astazyx |
Upload Date | July 12 2025 05:07 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,3 |
Motherboard | MacBookPro18,3 |
CPU Information | |
---|---|
Name | Apple M1 Pro |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M1 Pro |
Base Frequency | 3.22 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1333
248.0 IPS |
|
Image Classification (HP)
|
100% |
6897
1.28 KIPS |
|
Image Classification (Q)
|
96% |
6581
1.23 KIPS |
|
Image Segmentation (SP)
|
100% |
1503
24.4 IPS |
|
Image Segmentation (HP)
|
100% |
9692
157.1 IPS |
|
Image Segmentation (Q)
|
99% |
10435
169.2 IPS |
|
Pose Estimation (SP)
|
100% |
11083
12.9 IPS |
|
Pose Estimation (HP)
|
100% |
70376
82.1 IPS |
|
Pose Estimation (Q)
|
95% |
65818
77.1 IPS |
|
Object Detection (SP)
|
100% |
1553
123.2 IPS |
|
Object Detection (HP)
|
99% |
7997
636.1 IPS |
|
Object Detection (Q)
|
91% |
7521
601.0 IPS |
|
Face Detection (SP)
|
100% |
3255
38.7 IPS |
|
Face Detection (HP)
|
100% |
16091
191.2 IPS |
|
Face Detection (Q)
|
100% |
15064
179.0 IPS |
|
Depth Estimation (SP)
|
100% |
5814
44.8 IPS |
|
Depth Estimation (HP)
|
99% |
51476
396.6 IPS |
|
Depth Estimation (Q)
|
85% |
54198
423.5 IPS |
|
Style Transfer (SP)
|
100% |
21984
28.3 IPS |
|
Style Transfer (HP)
|
100% |
120938
155.5 IPS |
|
Style Transfer (Q)
|
96% |
115822
149.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4313
159.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
25972
959.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
28094
1.04 KIPS |
|
Text Classification (SP)
|
100% |
2286
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3973
5.30 KIPS |
|
Text Classification (Q)
|
93% |
4017
5.39 KIPS |
|
Machine Translation (SP)
|
100% |
3104
53.5 IPS |
|
Machine Translation (HP)
|
100% |
3599
62.0 IPS |
|
Machine Translation (Q)
|
98% |
3870
66.9 IPS |