Upload Date | April 14 2025 03:44 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,9 |
Motherboard | Mac15,9 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 2.79 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1235
229.7 IPS |
|
Image Classification (HP)
|
100% |
1961
364.7 IPS |
|
Image Classification (Q)
|
96% |
1389
259.5 IPS |
|
Image Segmentation (SP)
|
100% |
1533
24.8 IPS |
|
Image Segmentation (HP)
|
100% |
2251
36.5 IPS |
|
Image Segmentation (Q)
|
99% |
2582
41.9 IPS |
|
Pose Estimation (SP)
|
100% |
13205
15.4 IPS |
|
Pose Estimation (HP)
|
100% |
22927
26.8 IPS |
|
Pose Estimation (Q)
|
95% |
17339
20.3 IPS |
|
Object Detection (SP)
|
100% |
1591
126.2 IPS |
|
Object Detection (HP)
|
97% |
2401
191.2 IPS |
|
Object Detection (Q)
|
94% |
1695
135.1 IPS |
|
Face Detection (SP)
|
100% |
3210
38.1 IPS |
|
Face Detection (HP)
|
100% |
5269
62.6 IPS |
|
Face Detection (Q)
|
100% |
3021
35.9 IPS |
|
Depth Estimation (SP)
|
100% |
5892
45.4 IPS |
|
Depth Estimation (HP)
|
98% |
10380
80.2 IPS |
|
Depth Estimation (Q)
|
85% |
7286
57.0 IPS |
|
Style Transfer (SP)
|
100% |
24862
32.0 IPS |
|
Style Transfer (HP)
|
100% |
34371
44.2 IPS |
|
Style Transfer (Q)
|
96% |
27042
34.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4804
177.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
6257
231.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
3981
147.0 IPS |
|
Text Classification (SP)
|
100% |
2187
2.92 KIPS |
|
Text Classification (HP)
|
100% |
3801
5.07 KIPS |
|
Text Classification (Q)
|
93% |
3828
5.14 KIPS |
|
Machine Translation (SP)
|
100% |
3792
65.3 IPS |
|
Machine Translation (HP)
|
98% |
5728
99.0 IPS |
|
Machine Translation (Q)
|
98% |
5787
100.0 IPS |