User | benchmark_agent |
Upload Date | April 09 2025 12:48 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.4 (Build 24E248) |
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% |
8685
1.62 KIPS |
|
Image Classification (HP)
|
100% |
8450
1.57 KIPS |
|
Image Classification (Q)
|
96% |
7784
1.45 KIPS |
|
Image Segmentation (SP)
|
100% |
19783
320.7 IPS |
|
Image Segmentation (HP)
|
100% |
20739
336.2 IPS |
|
Image Segmentation (Q)
|
99% |
19814
321.2 IPS |
|
Pose Estimation (SP)
|
100% |
92175
107.6 IPS |
|
Pose Estimation (HP)
|
100% |
95435
111.4 IPS |
|
Pose Estimation (Q)
|
96% |
91609
107.3 IPS |
|
Object Detection (SP)
|
100% |
7480
593.4 IPS |
|
Object Detection (HP)
|
100% |
8638
685.2 IPS |
|
Object Detection (Q)
|
92% |
7808
623.2 IPS |
|
Face Detection (SP)
|
100% |
32604
387.4 IPS |
|
Face Detection (HP)
|
100% |
37676
447.7 IPS |
|
Face Detection (Q)
|
100% |
29786
353.9 IPS |
|
Depth Estimation (SP)
|
100% |
38882
299.6 IPS |
|
Depth Estimation (HP)
|
99% |
41216
317.5 IPS |
|
Depth Estimation (Q)
|
85% |
38212
298.8 IPS |
|
Style Transfer (SP)
|
100% |
190681
245.1 IPS |
|
Style Transfer (HP)
|
100% |
210637
270.8 IPS |
|
Style Transfer (Q)
|
96% |
196559
253.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
25080
926.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
26656
984.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
22775
841.0 IPS |
|
Text Classification (SP)
|
100% |
2909
3.88 KIPS |
|
Text Classification (HP)
|
100% |
4768
6.36 KIPS |
|
Text Classification (Q)
|
93% |
4829
6.48 KIPS |
|
Machine Translation (SP)
|
100% |
5071
87.4 IPS |
|
Machine Translation (HP)
|
100% |
5274
90.8 IPS |
|
Machine Translation (Q)
|
98% |
5275
91.2 IPS |