User | ITSNT |
Upload Date | January 24 2025 03:53 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D5055b) |
Model | MacBook Pro (16-inch, 2023) |
Model ID | Mac14,6 |
Motherboard | Mac14,6 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.63 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6545
1.22 KIPS |
|
Image Classification (HP)
|
100% |
6647
1.24 KIPS |
|
Image Classification (Q)
|
97% |
5838
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
12472
202.2 IPS |
|
Image Segmentation (HP)
|
100% |
12159
197.1 IPS |
|
Image Segmentation (Q)
|
99% |
11947
193.7 IPS |
|
Pose Estimation (SP)
|
100% |
82699
96.5 IPS |
|
Pose Estimation (HP)
|
100% |
86675
101.1 IPS |
|
Pose Estimation (Q)
|
95% |
81199
95.2 IPS |
|
Object Detection (SP)
|
100% |
6212
492.7 IPS |
|
Object Detection (HP)
|
100% |
6577
521.7 IPS |
|
Object Detection (Q)
|
91% |
5733
458.1 IPS |
|
Face Detection (SP)
|
100% |
27956
332.2 IPS |
|
Face Detection (HP)
|
100% |
28160
334.6 IPS |
|
Face Detection (Q)
|
100% |
21387
254.1 IPS |
|
Depth Estimation (SP)
|
100% |
33128
255.2 IPS |
|
Depth Estimation (HP)
|
99% |
33534
258.4 IPS |
|
Depth Estimation (Q)
|
85% |
28555
223.2 IPS |
|
Style Transfer (SP)
|
100% |
135035
173.6 IPS |
|
Style Transfer (HP)
|
100% |
154169
198.2 IPS |
|
Style Transfer (Q)
|
96% |
142150
183.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
20083
741.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
20487
756.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
16841
621.9 IPS |
|
Text Classification (SP)
|
100% |
2191
2.92 KIPS |
|
Text Classification (HP)
|
100% |
3793
5.06 KIPS |
|
Text Classification (Q)
|
93% |
3814
5.12 KIPS |
|
Machine Translation (SP)
|
100% |
1729
29.8 IPS |
|
Machine Translation (HP)
|
100% |
1589
27.4 IPS |
|
Machine Translation (Q)
|
98% |
1609
27.8 IPS |