Task semantic segmentation · model-size class mobile-class CNN · batch 1 · 7 platforms
✓ Like-for-like: same model-size class and batch.
| Platform | Result | Model · precision · stack | Grade | Power | Price | Fit perf/power/budget | Source |
|---|---|---|---|---|---|---|---|
| Hailo-10H (M.2/PCIe, x86 host) | 667 FPS throughput b=1 | unet_mobilenet_v2 INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) | D | 2.50 W reported in result source — spec | unknown | – / – / – | Hailo Model Zoo public models (Hailo-10H) |
| Hailo-8 (M.2/PCIe, x86 host) | 662 FPS throughput b=1 | unet_mobilenet_v2 INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) | D | 2.50 W reported in result source — spec | unknown | – / – / – | Hailo Model Zoo public models (Hailo-8) |
| Qualcomm Snapdragon X2 Elite (CRD) | 609 FPS inference_time b=1 | deeplabv3_plus_mobilenet w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) | D | unknown no power published | unknown | – / – / – | Qualcomm AI Hub Models perf.yaml (BSD-3) |
| Qualcomm Snapdragon X Elite (CRD) | 274 FPS inference_time b=1 | deeplabv3_plus_mobilenet w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) | D | unknown no power published | unknown | – / – / – | Qualcomm AI Hub Models perf.yaml (BSD-3) |
| Qualcomm Dragonwing IQ-9075 EVK | 270 FPS inference_time b=1 | deeplabv3_plus_mobilenet w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) | D | unknown no power published | unknown | – / – / – | Qualcomm AI Hub Models perf.yaml (BSD-3) |
| Hailo-8L (M.2/PCIe, x86 host) | 99.10 FPS throughput b=1 | unet_mobilenet_v2 INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) | D | 1.50 W reported in result source — spec | unknown | – / – / – | Hailo Model Zoo public models (Hailo-8L) |
| Qualcomm Dragonwing RB3 Gen 2 (QCS6490) | 71.69 FPS inference_time b=1 | deeplabv3_plus_mobilenet w8a8 · Qualcomm AI Hub onnx (QAIRT 2.50.0.260828221209) | D | unknown no power published | unknown | – / – / – | Qualcomm AI Hub Models perf.yaml (BSD-3) |
Confidence: A audited MLPerf closed, B documented third-party, C community, D vendor-published, E estimate. Unknown is never assumed. Other like-for-like groups: mobile-class CNN b1 (7); mid-size CNN b1 (7); mobile-class CNN b8 (3); mid-size CNN b8 (3); nano (YOLO-n) b1 (3); mid-size CNN bunknown (6); mobile-class CNN bunknown (4); unknown bunknown (6)