User | Qetesh |
Upload Date | August 16 2024 09:23 AM |
Views | 15 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,9 |
Motherboard | Mac15,9 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.04 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7819
1.45 KIPS |
|
Image Classification (HP)
|
100% |
8122
1.51 KIPS |
|
Image Classification (Q)
|
99% |
7469
1.39 KIPS |
|
Image Segmentation (SP)
|
100% |
16960
274.9 IPS |
|
Image Segmentation (HP)
|
100% |
17704
287.0 IPS |
|
Image Segmentation (Q)
|
100% |
17102
277.2 IPS |
|
Pose Estimation (SP)
|
100% |
92616
108.1 IPS |
|
Pose Estimation (HP)
|
100% |
95541
111.5 IPS |
|
Pose Estimation (Q)
|
97% |
83832
98.2 IPS |
|
Object Detection (SP)
|
100% |
7124
565.1 IPS |
|
Object Detection (HP)
|
100% |
8066
639.8 IPS |
|
Object Detection (Q)
|
91% |
6921
553.1 IPS |
|
Face Detection (SP)
|
100% |
31409
373.2 IPS |
|
Face Detection (HP)
|
100% |
32875
390.6 IPS |
|
Face Detection (Q)
|
100% |
24169
287.2 IPS |
|
Depth Estimation (SP)
|
100% |
38025
293.0 IPS |
|
Depth Estimation (HP)
|
99% |
40799
314.3 IPS |
|
Depth Estimation (Q)
|
97% |
6053
46.8 IPS |
|
Style Transfer (SP)
|
100% |
187999
241.7 IPS |
|
Style Transfer (HP)
|
100% |
204870
263.4 IPS |
|
Style Transfer (Q)
|
100% |
197910
254.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
23979
885.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
25661
947.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
18552
687.3 IPS |
|
Text Classification (SP)
|
100% |
2789
3.72 KIPS |
|
Text Classification (HP)
|
100% |
4880
6.51 KIPS |
|
Text Classification (Q)
|
93% |
4879
6.55 KIPS |
|
Machine Translation (SP)
|
100% |
1037
17.9 IPS |
|
Machine Translation (HP)
|
100% |
1156
19.9 IPS |
|
Machine Translation (Q)
|
98% |
1226
21.2 IPS |