User | Coin1news |
Upload Date | December 07 2024 01:32 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | MacBook Pro (16-inch, 2021) |
Model ID | MacBookPro18,2 |
Motherboard | MacBookPro18,2 |
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 | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1396
259.5 IPS |
|
Image Classification (HP)
|
100% |
2117
393.7 IPS |
|
Image Classification (Q)
|
96% |
1537
287.0 IPS |
|
Image Segmentation (SP)
|
100% |
1704
27.6 IPS |
|
Image Segmentation (HP)
|
100% |
2486
40.3 IPS |
|
Image Segmentation (Q)
|
99% |
2753
44.6 IPS |
|
Pose Estimation (SP)
|
100% |
11138
13.0 IPS |
|
Pose Estimation (HP)
|
100% |
22488
26.2 IPS |
|
Pose Estimation (Q)
|
95% |
17742
20.8 IPS |
|
Object Detection (SP)
|
100% |
1643
130.3 IPS |
|
Object Detection (HP)
|
97% |
2476
197.1 IPS |
|
Object Detection (Q)
|
94% |
1817
144.8 IPS |
|
Face Detection (SP)
|
100% |
3381
40.2 IPS |
|
Face Detection (HP)
|
100% |
5481
65.1 IPS |
|
Face Detection (Q)
|
100% |
3277
38.9 IPS |
|
Depth Estimation (SP)
|
100% |
6060
46.7 IPS |
|
Depth Estimation (HP)
|
98% |
10999
85.0 IPS |
|
Depth Estimation (Q)
|
85% |
7254
56.7 IPS |
|
Style Transfer (SP)
|
100% |
23130
29.7 IPS |
|
Style Transfer (HP)
|
100% |
36179
46.5 IPS |
|
Style Transfer (Q)
|
96% |
28028
36.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4579
169.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
6558
242.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
4236
156.4 IPS |
|
Text Classification (SP)
|
100% |
2313
3.09 KIPS |
|
Text Classification (HP)
|
100% |
4039
5.39 KIPS |
|
Text Classification (Q)
|
93% |
4020
5.40 KIPS |
|
Machine Translation (SP)
|
100% |
3575
61.6 IPS |
|
Machine Translation (HP)
|
98% |
3578
61.8 IPS |
|
Machine Translation (Q)
|
98% |
5154
89.1 IPS |