User | danb |
Upload Date | October 30 2024 02:52 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
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 | 3.82 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
8607
1.60 KIPS |
|
Image Classification (HP)
|
100% |
8883
1.65 KIPS |
|
Image Classification (Q)
|
97% |
7727
1.44 KIPS |
|
Image Segmentation (SP)
|
100% |
17347
281.2 IPS |
|
Image Segmentation (HP)
|
100% |
18171
294.6 IPS |
|
Image Segmentation (Q)
|
99% |
18842
305.4 IPS |
|
Pose Estimation (SP)
|
100% |
93689
109.3 IPS |
|
Pose Estimation (HP)
|
100% |
96950
113.1 IPS |
|
Pose Estimation (Q)
|
95% |
91272
107.0 IPS |
|
Object Detection (SP)
|
100% |
8202
650.6 IPS |
|
Object Detection (HP)
|
100% |
8934
708.7 IPS |
|
Object Detection (Q)
|
91% |
7745
618.9 IPS |
|
Face Detection (SP)
|
100% |
34407
408.8 IPS |
|
Face Detection (HP)
|
100% |
35409
420.7 IPS |
|
Face Detection (Q)
|
100% |
28442
337.9 IPS |
|
Depth Estimation (SP)
|
100% |
40339
310.8 IPS |
|
Depth Estimation (HP)
|
99% |
42992
331.2 IPS |
|
Depth Estimation (Q)
|
85% |
35902
280.6 IPS |
|
Style Transfer (SP)
|
100% |
193286
248.5 IPS |
|
Style Transfer (HP)
|
100% |
208836
268.5 IPS |
|
Style Transfer (Q)
|
96% |
196242
253.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
26396
974.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
27773
1.03 KIPS |
|
Image Super-Resolution (Q)
|
99% |
23229
857.7 IPS |
|
Text Classification (SP)
|
100% |
3053
4.08 KIPS |
|
Text Classification (HP)
|
100% |
4840
6.46 KIPS |
|
Text Classification (Q)
|
93% |
4777
6.41 KIPS |
|
Machine Translation (SP)
|
100% |
2819
48.6 IPS |
|
Machine Translation (HP)
|
100% |
2400
41.3 IPS |
|
Machine Translation (Q)
|
98% |
2472
42.7 IPS |