User | Kozek |
Upload Date | December 05 2024 10:14 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B2091) |
Model | MacBook Pro (16-inch, 2024) |
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% |
2082
387.1 IPS |
|
Image Classification (HP)
|
100% |
17628
3.28 KIPS |
|
Image Classification (Q)
|
97% |
22280
4.16 KIPS |
|
Image Segmentation (SP)
|
100% |
2460
39.9 IPS |
|
Image Segmentation (HP)
|
100% |
23245
376.8 IPS |
|
Image Segmentation (Q)
|
99% |
32310
523.8 IPS |
|
Pose Estimation (SP)
|
100% |
18998
22.2 IPS |
|
Pose Estimation (HP)
|
100% |
123501
144.1 IPS |
|
Pose Estimation (Q)
|
95% |
231151
270.9 IPS |
|
Object Detection (SP)
|
100% |
2471
196.0 IPS |
|
Object Detection (HP)
|
100% |
19856
1.57 KIPS |
|
Object Detection (Q)
|
91% |
24307
1.94 KIPS |
|
Face Detection (SP)
|
100% |
4625
55.0 IPS |
|
Face Detection (HP)
|
100% |
44940
534.0 IPS |
|
Face Detection (Q)
|
100% |
64042
761.0 IPS |
|
Depth Estimation (SP)
|
100% |
8815
67.9 IPS |
|
Depth Estimation (HP)
|
99% |
111151
856.4 IPS |
|
Depth Estimation (Q)
|
85% |
178596
1.40 KIPS |
|
Style Transfer (SP)
|
100% |
35481
45.6 IPS |
|
Style Transfer (HP)
|
100% |
237629
305.5 IPS |
|
Style Transfer (Q)
|
96% |
301816
389.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
7027
259.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
46938
1.73 KIPS |
|
Image Super-Resolution (Q)
|
99% |
79264
2.93 KIPS |
|
Text Classification (SP)
|
100% |
2930
3.91 KIPS |
|
Text Classification (HP)
|
100% |
5067
6.76 KIPS |
|
Text Classification (Q)
|
93% |
4914
6.60 KIPS |
|
Machine Translation (SP)
|
100% |
5747
99.0 IPS |
|
Machine Translation (HP)
|
100% |
16353
281.7 IPS |
|
Machine Translation (Q)
|
98% |
16424
283.8 IPS |