Task instance segmentation · model-size class nano (YOLO-n) · batch 1 · 5 platforms
✓ Like-for-like: same model-size class and batch.
| Platform | Result | Model · precision · stack | Grade | Power | Price | Fit perf/power/budget | Source |
|---|---|---|---|---|---|---|---|
| Hailo-8 (M.2/PCIe, x86 host) | 528 FPS throughput b=1 | yolov8n_seg INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) | D | 2.50 W reported in result source — spec | unknown | – / – / unknown | Hailo Model Zoo public models (Hailo-8) |
| Hailo-10H (M.2/PCIe, x86 host) | 311 FPS throughput b=1 | yolov8n_seg INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) | D | 2.50 W reported in result source — spec | unknown | – / – / unknown | Hailo Model Zoo public models (Hailo-10H) |
| Hailo-8L (M.2/PCIe, x86 host) | 168 FPS throughput b=1 | yolov8n_seg INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) | D | 1.50 W reported in result source — spec | unknown | – / – / unknown | Hailo Model Zoo public models (Hailo-8L) |
| Apple M4 (10-core GPU, 120 GB/s) | 196 FPS latency_e2e b=1 | YOLO26n-seg FP16 · Ultralytics 8.4.168 Core AI (coreai-torch 0.4.3), macOS 27.0 | B | unknown no power published | unknown | – / – / unknown | Ultralytics docs: Apple Core AI integration benchmark |
| Microchip PolarFire SoC Video Kit (VectorBlox CoreVectorBlox) | 14.13 FPS inference_time b=1 | yolov8n-seg INT8 (VNNX) · VectorBlox SDK (VNNX), no compression | D | unknown no power published | unknown | – / – / unknown | Microchip VectorBlox SDK tutorial metrics |
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: nano (YOLO-n) b1 (5); medium (YOLO-m) b1 (3); medium (YOLO-m) b8 (3); nano (YOLO-n) b8 (3); small (YOLO-s) b1 (3); small (YOLO-s) b8 (3); unknown b1 (4)