User | Jeffnt326 |
Upload Date | May 21 2025 06:25 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2082
387.2 IPS |
|
Image Classification (HP)
|
100% |
17512
3.26 KIPS |
|
Image Classification (Q)
|
97% |
21931
4.09 KIPS |
|
Image Segmentation (SP)
|
100% |
2257
36.6 IPS |
|
Image Segmentation (HP)
|
100% |
23194
376.0 IPS |
|
Image Segmentation (Q)
|
99% |
32154
521.2 IPS |
|
Pose Estimation (SP)
|
100% |
17410
20.3 IPS |
|
Pose Estimation (HP)
|
100% |
122527
143.0 IPS |
|
Pose Estimation (Q)
|
95% |
229833
269.4 IPS |
|
Object Detection (SP)
|
100% |
2496
198.0 IPS |
|
Object Detection (HP)
|
100% |
19680
1.56 KIPS |
|
Object Detection (Q)
|
91% |
23827
1.90 KIPS |
|
Face Detection (SP)
|
100% |
4581
54.4 IPS |
|
Face Detection (HP)
|
100% |
42588
506.0 IPS |
|
Face Detection (Q)
|
100% |
56359
669.7 IPS |
|
Depth Estimation (SP)
|
100% |
8617
66.4 IPS |
|
Depth Estimation (HP)
|
99% |
106635
821.6 IPS |
|
Depth Estimation (Q)
|
85% |
177617
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
25616
32.9 IPS |
|
Style Transfer (HP)
|
100% |
238440
306.5 IPS |
|
Style Transfer (Q)
|
96% |
297186
383.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5964
220.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
46237
1.71 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78375
2.89 KIPS |
|
Text Classification (SP)
|
100% |
2881
3.85 KIPS |
|
Text Classification (HP)
|
100% |
5379
7.18 KIPS |
|
Text Classification (Q)
|
93% |
6376
8.56 KIPS |
|
Machine Translation (SP)
|
100% |
5633
97.0 IPS |
|
Machine Translation (HP)
|
100% |
16382
282.2 IPS |
|
Machine Translation (Q)
|
98% |
16286
281.4 IPS |