User | tntoak |
Upload Date | August 18 2024 07:28 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.47 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1381
256.8 IPS |
|
Image Classification (HP)
|
100% |
13251
2.46 KIPS |
|
Image Classification (Q)
|
99% |
16269
3.03 KIPS |
|
Image Segmentation (SP)
|
100% |
1682
27.3 IPS |
|
Image Segmentation (HP)
|
100% |
9284
150.5 IPS |
|
Image Segmentation (Q)
|
100% |
9311
150.9 IPS |
|
Pose Estimation (SP)
|
100% |
12970
15.1 IPS |
|
Pose Estimation (HP)
|
100% |
103929
121.3 IPS |
|
Pose Estimation (Q)
|
94% |
98160
115.1 IPS |
|
Object Detection (SP)
|
100% |
1676
132.9 IPS |
|
Object Detection (HP)
|
99% |
13864
1.10 KIPS |
|
Object Detection (Q)
|
91% |
16910
1.35 KIPS |
|
Face Detection (SP)
|
100% |
3639
43.2 IPS |
|
Face Detection (HP)
|
100% |
23819
283.0 IPS |
|
Face Detection (Q)
|
100% |
36444
433.0 IPS |
|
Depth Estimation (SP)
|
100% |
6178
47.6 IPS |
|
Depth Estimation (HP)
|
99% |
73277
564.6 IPS |
|
Depth Estimation (Q)
|
97% |
81523
630.4 IPS |
|
Style Transfer (SP)
|
100% |
24797
31.9 IPS |
|
Style Transfer (HP)
|
100% |
156607
201.3 IPS |
|
Style Transfer (Q)
|
100% |
157478
202.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5078
187.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
40586
1.50 KIPS |
|
Image Super-Resolution (Q)
|
98% |
47357
1.75 KIPS |
|
Text Classification (SP)
|
100% |
2230
2.98 KIPS |
|
Text Classification (HP)
|
100% |
3834
5.12 KIPS |
|
Text Classification (Q)
|
93% |
3865
5.19 KIPS |
|
Machine Translation (SP)
|
100% |
4554
78.4 IPS |
|
Machine Translation (HP)
|
100% |
2018
34.8 IPS |
|
Machine Translation (Q)
|
98% |
1974
34.1 IPS |