User | holgr |
Upload Date | November 03 2024 07:04 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
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 | 3.09 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5582
1.04 KIPS |
|
Image Classification (HP)
|
100% |
5745
1.07 KIPS |
|
Image Classification (Q)
|
97% |
4869
908.6 IPS |
|
Image Segmentation (SP)
|
100% |
10388
168.4 IPS |
|
Image Segmentation (HP)
|
100% |
10599
171.8 IPS |
|
Image Segmentation (Q)
|
99% |
10758
174.4 IPS |
|
Pose Estimation (SP)
|
100% |
57114
66.6 IPS |
|
Pose Estimation (HP)
|
100% |
60480
70.6 IPS |
|
Pose Estimation (Q)
|
95% |
55526
65.1 IPS |
|
Object Detection (SP)
|
100% |
4500
357.0 IPS |
|
Object Detection (HP)
|
100% |
5032
399.2 IPS |
|
Object Detection (Q)
|
91% |
4762
380.5 IPS |
|
Face Detection (SP)
|
100% |
21640
257.1 IPS |
|
Face Detection (HP)
|
100% |
22572
268.2 IPS |
|
Face Detection (Q)
|
100% |
15748
187.1 IPS |
|
Depth Estimation (SP)
|
100% |
26484
204.0 IPS |
|
Depth Estimation (HP)
|
99% |
28221
217.4 IPS |
|
Depth Estimation (Q)
|
85% |
23135
180.8 IPS |
|
Style Transfer (SP)
|
100% |
96925
124.6 IPS |
|
Style Transfer (HP)
|
100% |
121169
155.8 IPS |
|
Style Transfer (Q)
|
96% |
113210
146.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
17142
633.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
17321
639.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
14184
523.7 IPS |
|
Text Classification (SP)
|
100% |
2310
3.08 KIPS |
|
Text Classification (HP)
|
100% |
4006
5.35 KIPS |
|
Text Classification (Q)
|
93% |
3976
5.34 KIPS |
|
Machine Translation (SP)
|
100% |
818
14.1 IPS |
|
Machine Translation (HP)
|
100% |
976
16.8 IPS |
|
Machine Translation (Q)
|
98% |
959
16.6 IPS |