User | B0Besh |
Upload Date | May 03 2025 09:25 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
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% |
2071
385.2 IPS |
|
Image Classification (HP)
|
100% |
17337
3.22 KIPS |
|
Image Classification (Q)
|
97% |
22833
4.26 KIPS |
|
Image Segmentation (SP)
|
100% |
2274
36.9 IPS |
|
Image Segmentation (HP)
|
100% |
23336
378.3 IPS |
|
Image Segmentation (Q)
|
99% |
32245
522.7 IPS |
|
Pose Estimation (SP)
|
100% |
17125
20.0 IPS |
|
Pose Estimation (HP)
|
100% |
122657
143.1 IPS |
|
Pose Estimation (Q)
|
95% |
229628
269.1 IPS |
|
Object Detection (SP)
|
100% |
2476
196.4 IPS |
|
Object Detection (HP)
|
100% |
19949
1.58 KIPS |
|
Object Detection (Q)
|
91% |
23695
1.89 KIPS |
|
Face Detection (SP)
|
100% |
4647
55.2 IPS |
|
Face Detection (HP)
|
100% |
45477
540.4 IPS |
|
Face Detection (Q)
|
100% |
56628
672.9 IPS |
|
Depth Estimation (SP)
|
100% |
8669
66.8 IPS |
|
Depth Estimation (HP)
|
99% |
107344
827.0 IPS |
|
Depth Estimation (Q)
|
85% |
176795
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
25648
33.0 IPS |
|
Style Transfer (HP)
|
100% |
238172
306.2 IPS |
|
Style Transfer (Q)
|
96% |
302028
389.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5966
220.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
46536
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78219
2.89 KIPS |
|
Text Classification (SP)
|
100% |
2881
3.85 KIPS |
|
Text Classification (HP)
|
100% |
5291
7.06 KIPS |
|
Text Classification (Q)
|
93% |
6119
8.21 KIPS |
|
Machine Translation (SP)
|
100% |
5572
96.0 IPS |
|
Machine Translation (HP)
|
100% |
16269
280.2 IPS |
|
Machine Translation (Q)
|
98% |
16443
284.2 IPS |