User | Jamault |
Upload Date | December 28 2024 07:19 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
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 | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7918
1.47 KIPS |
|
Image Classification (HP)
|
100% |
8372
1.56 KIPS |
|
Image Classification (Q)
|
97% |
7221
1.35 KIPS |
|
Image Segmentation (SP)
|
100% |
16667
270.2 IPS |
|
Image Segmentation (HP)
|
100% |
17345
281.2 IPS |
|
Image Segmentation (Q)
|
99% |
17943
290.9 IPS |
|
Pose Estimation (SP)
|
100% |
92216
107.6 IPS |
|
Pose Estimation (HP)
|
100% |
95464
111.4 IPS |
|
Pose Estimation (Q)
|
95% |
89269
104.6 IPS |
|
Object Detection (SP)
|
100% |
7879
625.0 IPS |
|
Object Detection (HP)
|
100% |
8426
668.4 IPS |
|
Object Detection (Q)
|
91% |
7229
577.7 IPS |
|
Face Detection (SP)
|
100% |
32335
384.2 IPS |
|
Face Detection (HP)
|
100% |
35742
424.7 IPS |
|
Face Detection (Q)
|
100% |
26504
314.9 IPS |
|
Depth Estimation (SP)
|
100% |
38224
294.5 IPS |
|
Depth Estimation (HP)
|
99% |
41039
316.2 IPS |
|
Depth Estimation (Q)
|
85% |
33896
264.9 IPS |
|
Style Transfer (SP)
|
100% |
187179
240.6 IPS |
|
Style Transfer (HP)
|
100% |
204810
263.3 IPS |
|
Style Transfer (Q)
|
96% |
189197
244.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
25347
936.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
25566
944.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
21414
790.7 IPS |
|
Text Classification (SP)
|
100% |
2722
3.63 KIPS |
|
Text Classification (HP)
|
100% |
4773
6.37 KIPS |
|
Text Classification (Q)
|
93% |
4697
6.30 KIPS |
|
Machine Translation (SP)
|
100% |
2854
49.2 IPS |
|
Machine Translation (HP)
|
100% |
2936
50.6 IPS |
|
Machine Translation (Q)
|
98% |
2612
45.1 IPS |