What is the best board for YOLO object detection?
Hailo-8 (M.2/PCIe, x86 host): 1036 FPS (yolov8n, INT8 (Hailo quantized); grade D; undated). Next: NVIDIA DGX Spark 990 FPS; Hailo-10H (M.2/PCIe, x86 host) 375 FPS. Like-for-like group: nano (YOLO-n), batch 1.
| # | Platform | Result | Perf/W | Price | Grade · date | Source |
|---|---|---|---|---|---|---|
| 1 | Hailo-8 (M.2/PCIe, x86 host) | 1036 FPS yolov8n · INT8 (Hailo quantized) | 414 spec | unknown | D undated | Hailo Model Zoo public models (Hailo-8) |
| 2 | NVIDIA DGX Spark | 990 FPS YOLO11n · FP16 | 6.47 spec | $4699 | B undated | Ultralytics docs benchmark table |
| 3 | Hailo-10H (M.2/PCIe, x86 host) | 375 FPS yolov8n · INT8 (Hailo quantized) | 150 spec | unknown | D undated | Hailo Model Zoo public models (Hailo-10H) |
| 4 | NVIDIA Jetson AGX Thor | 719 FPS YOLO26n · FP16 | 5.53 spec | $3499 | B undated | Ultralytics docs benchmark table |
| 5 | Apple M4 (10-core GPU, 120 GB/s) | 357 FPS YOLO26n · FP16 | unknown | unknown | B 2026 (year only) | Ultralytics docs: Apple Core AI integration benchmark |
Filters: task=object detection. Ranking: boards that meet every known target, then headroom and perf/W; unknown power or price is not penalised. Open in /find · JSON
Sources
- https://github.com/hailo-ai/hailo_model_zoo/tree/v2.20.0/docs/public_models/HAILO8
- https://docs.ultralytics.com/guides/nvidia-dgx-spark/
- https://github.com/hailo-ai/hailo_model_zoo/tree/v5.4.0/docs/public_models/HAILO10H
- https://docs.ultralytics.com/guides/nvidia-jetson/
- https://docs.ultralytics.com/integrations/coreai/
Generated 2026-10-16 from HWBench data only. All answers · Submit a result
Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.