User | tony84 |
Upload Date | June 15 2025 08:03 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.5 (Build 24F74) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,4 |
Motherboard | MacBookPro18,4 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4390
816.5 IPS |
|
Image Classification (HP)
|
100% |
4507
838.2 IPS |
|
Image Classification (Q)
|
96% |
4464
833.6 IPS |
|
Image Segmentation (SP)
|
100% |
10019
162.4 IPS |
|
Image Segmentation (HP)
|
100% |
9889
160.3 IPS |
|
Image Segmentation (Q)
|
99% |
9417
152.7 IPS |
|
Pose Estimation (SP)
|
100% |
47390
55.3 IPS |
|
Pose Estimation (HP)
|
100% |
50835
59.3 IPS |
|
Pose Estimation (Q)
|
96% |
48825
57.2 IPS |
|
Object Detection (SP)
|
100% |
4627
367.0 IPS |
|
Object Detection (HP)
|
100% |
4869
386.2 IPS |
|
Object Detection (Q)
|
92% |
4508
359.9 IPS |
|
Face Detection (SP)
|
100% |
18488
219.7 IPS |
|
Face Detection (HP)
|
100% |
18903
224.6 IPS |
|
Face Detection (Q)
|
100% |
16027
190.4 IPS |
|
Depth Estimation (SP)
|
100% |
23431
180.5 IPS |
|
Depth Estimation (HP)
|
99% |
24940
192.1 IPS |
|
Depth Estimation (Q)
|
86% |
22641
176.9 IPS |
|
Style Transfer (SP)
|
100% |
80559
103.6 IPS |
|
Style Transfer (HP)
|
100% |
96931
124.6 IPS |
|
Style Transfer (Q)
|
96% |
94504
122.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
15448
570.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
16326
602.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
14343
529.6 IPS |
|
Text Classification (SP)
|
100% |
2281
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3958
5.28 KIPS |
|
Text Classification (Q)
|
93% |
3971
5.33 KIPS |
|
Machine Translation (SP)
|
100% |
1655
28.5 IPS |
|
Machine Translation (HP)
|
100% |
1696
29.2 IPS |
|
Machine Translation (Q)
|
98% |
1335
23.1 IPS |