| User | MarkCX |
| Upload Date | March 05 2026 04:26 PM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M4 Max |
| System Information | |
|---|---|
| Operating System | macOS 26.3.1 (Build 25D2128) |
| Model | Mac Studio (2025) |
| Model ID | Mac16,9 |
| Motherboard | Mac16,9 |
| CPU Information | |
|---|---|
| Name | Apple M4 Max |
| Topology | 1 Processor, 14 Cores |
| Identifier | Apple M4 Max |
| Base Frequency | 4.50 GHz |
| Cluster 1 | 10 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 36.00 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
9328
1.73 KIPS |
|
|
Image Classification (HP)
|
100% |
9840
1.83 KIPS |
|
|
Image Classification (Q)
|
96% |
9479
1.77 KIPS |
|
|
Image Segmentation (SP)
|
100% |
20371
330.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
21413
347.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
20519
332.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
77204
90.1 IPS |
|
|
Pose Estimation (HP)
|
100% |
88383
103.1 IPS |
|
|
Pose Estimation (Q)
|
96% |
84744
99.3 IPS |
|
|
Object Detection (SP)
|
100% |
8771
695.8 IPS |
|
|
Object Detection (HP)
|
100% |
9437
748.5 IPS |
|
|
Object Detection (Q)
|
91% |
8419
672.9 IPS |
|
|
Face Detection (SP)
|
100% |
36635
435.3 IPS |
|
|
Face Detection (HP)
|
100% |
41436
492.3 IPS |
|
|
Face Detection (Q)
|
100% |
36832
437.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
42359
326.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
44862
345.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
41642
325.8 IPS |
|
|
Style Transfer (SP)
|
100% |
185078
237.9 IPS |
|
|
Style Transfer (HP)
|
100% |
201204
258.7 IPS |
|
|
Style Transfer (Q)
|
96% |
196217
253.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
26020
960.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
26918
993.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
23588
871.0 IPS |
|
|
Text Classification (SP)
|
100% |
3283
4.38 KIPS |
|
|
Text Classification (HP)
|
99% |
5675
7.57 KIPS |
|
|
Text Classification (Q)
|
93% |
5653
7.59 KIPS |
|
|
Machine Translation (SP)
|
100% |
7623
131.3 IPS |
|
|
Machine Translation (HP)
|
100% |
8372
144.2 IPS |
|
|
Machine Translation (Q)
|
98% |
7405
128.0 IPS |