User | benchmark_agent |
Upload Date | April 08 2025 05:02 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.7.4 (Build 23H420) |
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 | 4.05 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7151
1.33 KIPS |
|
Image Classification (HP)
|
100% |
7297
1.36 KIPS |
|
Image Classification (Q)
|
97% |
5773
1.08 KIPS |
|
Image Segmentation (SP)
|
100% |
15908
257.9 IPS |
|
Image Segmentation (HP)
|
100% |
16338
264.8 IPS |
|
Image Segmentation (Q)
|
99% |
16793
272.2 IPS |
|
Pose Estimation (SP)
|
100% |
90064
105.1 IPS |
|
Pose Estimation (HP)
|
100% |
93972
109.6 IPS |
|
Pose Estimation (Q)
|
97% |
83140
97.4 IPS |
|
Object Detection (SP)
|
100% |
7174
569.1 IPS |
|
Object Detection (HP)
|
100% |
7719
612.2 IPS |
|
Object Detection (Q)
|
92% |
6439
513.9 IPS |
|
Face Detection (SP)
|
100% |
27077
321.7 IPS |
|
Face Detection (HP)
|
100% |
29846
354.6 IPS |
|
Face Detection (Q)
|
100% |
21879
260.0 IPS |
|
Depth Estimation (SP)
|
100% |
37496
288.9 IPS |
|
Depth Estimation (HP)
|
99% |
40326
310.7 IPS |
|
Depth Estimation (Q)
|
1% |
0
277.4 IPS |
|
Style Transfer (SP)
|
100% |
186990
240.4 IPS |
|
Style Transfer (HP)
|
100% |
203268
261.3 IPS |
|
Style Transfer (Q)
|
96% |
184097
237.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
24733
913.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
25263
932.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
19366
715.1 IPS |
|
Text Classification (SP)
|
100% |
1433
1.91 KIPS |
|
Text Classification (HP)
|
100% |
842
1.12 KIPS |
|
Text Classification (Q)
|
93% |
1055
1.42 KIPS |
|
Machine Translation (SP)
|
100% |
1455
25.1 IPS |
|
Machine Translation (HP)
|
100% |
1696
29.2 IPS |
|
Machine Translation (Q)
|
98% |
1945
33.6 IPS |