User | teotwawk |
Upload Date | March 21 2025 12:13 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
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 | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2153
400.3 IPS |
|
Image Classification (HP)
|
100% |
17541
3.26 KIPS |
|
Image Classification (Q)
|
97% |
23669
4.42 KIPS |
|
Image Segmentation (SP)
|
100% |
2590
42.0 IPS |
|
Image Segmentation (HP)
|
100% |
23527
381.4 IPS |
|
Image Segmentation (Q)
|
99% |
33209
538.3 IPS |
|
Pose Estimation (SP)
|
100% |
18884
22.0 IPS |
|
Pose Estimation (HP)
|
100% |
123768
144.4 IPS |
|
Pose Estimation (Q)
|
95% |
230784
270.5 IPS |
|
Object Detection (SP)
|
100% |
2543
201.7 IPS |
|
Object Detection (HP)
|
100% |
20896
1.66 KIPS |
|
Object Detection (Q)
|
91% |
26209
2.09 KIPS |
|
Face Detection (SP)
|
100% |
4641
55.1 IPS |
|
Face Detection (HP)
|
100% |
44953
534.1 IPS |
|
Face Detection (Q)
|
100% |
56441
670.6 IPS |
|
Depth Estimation (SP)
|
100% |
8872
68.4 IPS |
|
Depth Estimation (HP)
|
99% |
112239
864.7 IPS |
|
Depth Estimation (Q)
|
85% |
181957
1.42 KIPS |
|
Style Transfer (SP)
|
100% |
35626
45.8 IPS |
|
Style Transfer (HP)
|
100% |
239095
307.4 IPS |
|
Style Transfer (Q)
|
96% |
309069
398.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
7191
265.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
47124
1.74 KIPS |
|
Image Super-Resolution (Q)
|
99% |
81221
3.00 KIPS |
|
Text Classification (SP)
|
100% |
2948
3.94 KIPS |
|
Text Classification (HP)
|
100% |
6235
8.32 KIPS |
|
Text Classification (Q)
|
93% |
5374
7.21 KIPS |
|
Machine Translation (SP)
|
100% |
5874
101.2 IPS |
|
Machine Translation (HP)
|
100% |
16782
289.1 IPS |
|
Machine Translation (Q)
|
98% |
16737
289.2 IPS |