User | Jetsada |
Upload Date | September 20 2025 06:56 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A354) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,9 |
Motherboard | Mac14,9 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.49 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1365
253.9 IPS |
|
Image Classification (HP)
|
100% |
14817
2.76 KIPS |
|
Image Classification (Q)
|
96% |
17237
3.22 KIPS |
|
Image Segmentation (SP)
|
100% |
1633
26.5 IPS |
|
Image Segmentation (HP)
|
100% |
20180
327.1 IPS |
|
Image Segmentation (Q)
|
99% |
24996
405.2 IPS |
|
Pose Estimation (SP)
|
100% |
11971
14.0 IPS |
|
Pose Estimation (HP)
|
100% |
105791
123.4 IPS |
|
Pose Estimation (Q)
|
95% |
104485
122.5 IPS |
|
Object Detection (SP)
|
100% |
1642
130.2 IPS |
|
Object Detection (HP)
|
99% |
15361
1.22 KIPS |
|
Object Detection (Q)
|
91% |
17098
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3600
42.8 IPS |
|
Face Detection (HP)
|
100% |
36736
436.5 IPS |
|
Face Detection (Q)
|
100% |
47324
562.3 IPS |
|
Depth Estimation (SP)
|
100% |
6133
47.2 IPS |
|
Depth Estimation (HP)
|
99% |
88621
682.8 IPS |
|
Depth Estimation (Q)
|
85% |
109244
853.7 IPS |
|
Style Transfer (SP)
|
100% |
25585
32.9 IPS |
|
Style Transfer (HP)
|
100% |
204650
263.1 IPS |
|
Style Transfer (Q)
|
96% |
192665
248.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4891
180.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
43524
1.61 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49230
1.82 KIPS |
|
Text Classification (SP)
|
100% |
2486
3.32 KIPS |
|
Text Classification (HP)
|
99% |
4136
5.52 KIPS |
|
Text Classification (Q)
|
93% |
4080
5.48 KIPS |
|
Machine Translation (SP)
|
100% |
4279
73.7 IPS |
|
Machine Translation (HP)
|
100% |
4138
71.3 IPS |
|
Machine Translation (Q)
|
98% |
4394
75.9 IPS |