User | anthonynelzin |
Upload Date | November 12 2024 10:31 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,7 |
Model ID | Mac16,7 |
Motherboard | Mac16,7 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 24.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2081
387.1 IPS |
|
Image Classification (HP)
|
100% |
17341
3.22 KIPS |
|
Image Classification (Q)
|
97% |
21995
4.10 KIPS |
|
Image Segmentation (SP)
|
100% |
2444
39.6 IPS |
|
Image Segmentation (HP)
|
100% |
23203
376.1 IPS |
|
Image Segmentation (Q)
|
99% |
32266
523.1 IPS |
|
Pose Estimation (SP)
|
100% |
18997
22.2 IPS |
|
Pose Estimation (HP)
|
100% |
123309
143.9 IPS |
|
Pose Estimation (Q)
|
95% |
229579
269.1 IPS |
|
Object Detection (SP)
|
100% |
2488
197.3 IPS |
|
Object Detection (HP)
|
100% |
19605
1.56 KIPS |
|
Object Detection (Q)
|
91% |
23763
1.90 KIPS |
|
Face Detection (SP)
|
100% |
4579
54.4 IPS |
|
Face Detection (HP)
|
100% |
44695
531.1 IPS |
|
Face Detection (Q)
|
100% |
63870
758.9 IPS |
|
Depth Estimation (SP)
|
100% |
8862
68.3 IPS |
|
Depth Estimation (HP)
|
99% |
105746
814.7 IPS |
|
Depth Estimation (Q)
|
85% |
177096
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
35572
45.7 IPS |
|
Style Transfer (HP)
|
100% |
233795
300.5 IPS |
|
Style Transfer (Q)
|
96% |
296778
383.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
6989
258.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
46114
1.70 KIPS |
|
Image Super-Resolution (Q)
|
99% |
78343
2.89 KIPS |
|
Text Classification (SP)
|
100% |
2927
3.91 KIPS |
|
Text Classification (HP)
|
100% |
4899
6.54 KIPS |
|
Text Classification (Q)
|
93% |
4842
6.50 KIPS |
|
Machine Translation (SP)
|
100% |
5736
98.8 IPS |
|
Machine Translation (HP)
|
100% |
16657
286.9 IPS |
|
Machine Translation (Q)
|
98% |
16389
283.2 IPS |