User | gbenchgs |
Upload Date | August 16 2024 12:32 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
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 | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4814
895.2 IPS |
|
Image Classification (HP)
|
100% |
4956
921.7 IPS |
|
Image Classification (Q)
|
99% |
4226
788.2 IPS |
|
Image Segmentation (SP)
|
100% |
9987
161.9 IPS |
|
Image Segmentation (HP)
|
100% |
10142
164.4 IPS |
|
Image Segmentation (Q)
|
100% |
9786
158.6 IPS |
|
Pose Estimation (SP)
|
100% |
56610
66.1 IPS |
|
Pose Estimation (HP)
|
100% |
59870
69.9 IPS |
|
Pose Estimation (Q)
|
97% |
52059
61.0 IPS |
|
Object Detection (SP)
|
100% |
5029
398.9 IPS |
|
Object Detection (HP)
|
100% |
5225
414.5 IPS |
|
Object Detection (Q)
|
91% |
4054
324.0 IPS |
|
Face Detection (SP)
|
100% |
21037
250.0 IPS |
|
Face Detection (HP)
|
100% |
21443
254.8 IPS |
|
Face Detection (Q)
|
100% |
14848
176.4 IPS |
|
Depth Estimation (SP)
|
100% |
26024
200.5 IPS |
|
Depth Estimation (HP)
|
99% |
26694
205.7 IPS |
|
Depth Estimation (Q)
|
97% |
6404
49.5 IPS |
|
Style Transfer (SP)
|
100% |
95356
122.6 IPS |
|
Style Transfer (HP)
|
100% |
118966
152.9 IPS |
|
Style Transfer (Q)
|
100% |
116892
150.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
16059
593.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
16581
612.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
11860
439.4 IPS |
|
Text Classification (SP)
|
100% |
2250
3.00 KIPS |
|
Text Classification (HP)
|
100% |
3744
5.00 KIPS |
|
Text Classification (Q)
|
93% |
3741
5.02 KIPS |
|
Machine Translation (SP)
|
100% |
966
16.6 IPS |
|
Machine Translation (HP)
|
100% |
1085
18.7 IPS |
|
Machine Translation (Q)
|
98% |
1200
20.7 IPS |