User | benchmark_agent |
Upload Date | April 08 2025 05:53 PM |
Views | 4 |
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 | 4.04 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7129
1.33 KIPS |
|
Image Classification (HP)
|
100% |
7313
1.36 KIPS |
|
Image Classification (Q)
|
97% |
5732
1.07 KIPS |
|
Image Segmentation (SP)
|
100% |
15644
253.6 IPS |
|
Image Segmentation (HP)
|
100% |
16550
268.3 IPS |
|
Image Segmentation (Q)
|
99% |
16461
266.8 IPS |
|
Pose Estimation (SP)
|
100% |
90507
105.6 IPS |
|
Pose Estimation (HP)
|
100% |
94501
110.3 IPS |
|
Pose Estimation (Q)
|
97% |
83430
97.7 IPS |
|
Object Detection (SP)
|
100% |
7226
573.2 IPS |
|
Object Detection (HP)
|
100% |
7687
609.7 IPS |
|
Object Detection (Q)
|
92% |
6460
515.6 IPS |
|
Face Detection (SP)
|
100% |
27330
324.7 IPS |
|
Face Detection (HP)
|
100% |
29988
356.3 IPS |
|
Face Detection (Q)
|
100% |
21712
258.0 IPS |
|
Depth Estimation (SP)
|
100% |
37424
288.3 IPS |
|
Depth Estimation (HP)
|
99% |
40762
314.0 IPS |
|
Depth Estimation (Q)
|
1% |
0
266.7 IPS |
|
Style Transfer (SP)
|
100% |
181241
233.0 IPS |
|
Style Transfer (HP)
|
100% |
199316
256.2 IPS |
|
Style Transfer (Q)
|
96% |
181223
233.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
24386
900.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
25269
933.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
19526
721.0 IPS |
|
Text Classification (SP)
|
100% |
511
682.4 IPS |
|
Text Classification (HP)
|
100% |
662
883.0 IPS |
|
Text Classification (Q)
|
93% |
754
1.01 KIPS |
|
Machine Translation (SP)
|
100% |
1700
29.3 IPS |
|
Machine Translation (HP)
|
100% |
1777
30.6 IPS |
|
Machine Translation (Q)
|
98% |
1958
33.8 IPS |