HWBench

Hailo-10H (M.2/PCIe, x86 host) vs Raspberry Pi 5 + AI HAT+ (Hailo-8)

Raspberry Pi AI HAT+ with Hailo-8 accelerator mounted on a Raspberry Pi, angled view
Raspberry Pi AI HAT+ (Hailo-8). Photo: SparkFun Electronics, CC BY 2.0, via Wikimedia Commons.

Hailo-10H (M.2/PCIe, x86 host) is faster in all 2 like-for-like comparisons (largest gap: object detection, 8.14×).

Hailo-10H (M.2/PCIe, x86 host)Raspberry Pi 5 + AI HAT+ (Hailo-8)
Best object detection375 FPS D
2026-09-03 (page last edited)
76.99 FPS C
2025-12-16 (page last edited)
Power2.50 W specn/a
Perf / W150 FPS/W specn/a
Pricen/an/a
Workloads with data5 of 73 of 7

Best published object detection result per platform (may be from different like-for-like groups — see data). n/a = not published; never estimated.

Show data — all workloads, sources and like-for-like groups

object detection

✓ Like-for-like: model-size class nano (YOLO-n), batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Hailo-10H (M.2/PCIe, x86 host)375 FPS
throughput · b=1
yolov8n
INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · nano (YOLO-n)
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-10H)
2026-09-03 (page last edited)
Raspberry Pi 5 + AI HAT+ (Hailo-8)46.08 FPS
inference_time · b=1
YOLO26n
INT8 · Ultralytics Hailo HEF / HailoRT · nano (YOLO-n)
Bunknown power n/a
no power published
Ultralytics documentation: Hailo integration benchmark
2026-10-11 (page last edited)
✓ Like-for-like: model-size class medium (YOLO-m), batch 8. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Hailo-10H (M.2/PCIe, x86 host)208 FPS
throughput · b=8
yolov5m_wo_spp
INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · medium (YOLO-m)
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-10H)
2026-09-03 (page last edited)
Raspberry Pi 5 + AI HAT+ (Hailo-8)76.99 FPS
FPS per stream, 1 stream(s) · b=8
yolov8m
INT8 · Hailo TAPPAS multi_stream_detection, HailoRT 4.19 · medium (YOLO-m)
Cunknown power n/a
no power published
Seeed Studio wiki: multistream inference on RPi5 + Hailo-8
2025-12-16 (page last edited)

instance segmentation

Only Hailo-10H (M.2/PCIe, x86 host) has published instance segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-10H (M.2/PCIe, x86 host)66.70 FPS
throughput · b=1
yolov8m_seg
INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · medium (YOLO-m)
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-10H)
2026-09-03 (page last edited)

Raspberry Pi 5 + AI HAT+ (Hailo-8):

◌

No published instance segmentation results for Raspberry Pi 5 + AI HAT+ (Hailo-8) or Hailo-10H (M.2/PCIe, x86 host) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

Only Hailo-10H (M.2/PCIe, x86 host) has published pose estimation results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-10H (M.2/PCIe, x86 host)2034 FPS
throughput · b=1
mspn_regnetx_800mf
INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · mid-size CNN
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-10H)
2026-09-03 (page last edited)

Raspberry Pi 5 + AI HAT+ (Hailo-8):

◌

No published pose estimation results for Raspberry Pi 5 + AI HAT+ (Hailo-8) or Hailo-10H (M.2/PCIe, x86 host) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

image classification

⚠ MIXED COMPARISON — not like-for-like. Baseline mobile-class CNN at batch 1. Differs: model-size class nano (YOLO-n) vs mobile-class CNN.
PlatformResultModel · precision · stackGradePowerSource
Hailo-10H (M.2/PCIe, x86 host)2798 FPS
throughput · b=1
mobilenet_v2_1.0
INT8 (Hailo quantized) · Hailo DFC v5.4.0 / HailoRT (model zoo) · mobile-class CNN
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-10H)
2026-09-03 (page last edited)
Raspberry Pi 5 + AI HAT+ (Hailo-8)
MIXED: model-size class nano (YOLO-n) vs mobile-class CNN
500 FPS
inference_time · b=1
YOLO26n-cls
INT8 · Ultralytics Hailo HEF / HailoRT · nano (YOLO-n)
Bunknown power n/a
no power published
Ultralytics documentation: Hailo integration benchmark
2026-10-11 (page last edited)

No shared like-for-like group exists for this pair.

semantic segmentation

⚠ MIXED COMPARISON — not like-for-like. Baseline mobile-class CNN at batch 1. Differs: model-size class nano (YOLO-n) vs mobile-class CNN.
PlatformResultModel · precision · stackGradePowerSource
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) · mobile-class CNN
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-10H)
2026-09-03 (page last edited)
Raspberry Pi 5 + AI HAT+ (Hailo-8)
MIXED: model-size class nano (YOLO-n) vs mobile-class CNN
28.74 FPS
inference_time · b=1
YOLO26n-sem
INT8 · Ultralytics Hailo HEF / HailoRT · nano (YOLO-n)
Bunknown power n/a
no power published
Ultralytics documentation: Hailo integration benchmark
2026-10-11 (page last edited)

No shared like-for-like group exists for this pair.

speech-to-text

◌

No published speech-to-text results for Hailo-10H (M.2/PCIe, x86 host) or Raspberry Pi 5 + AI HAT+ (Hailo-8) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

◌

No published LLM generation results for Hailo-10H (M.2/PCIe, x86 host) or Raspberry Pi 5 + AI HAT+ (Hailo-8) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

How to read these numbers
Every number is labelled. Confidence: A MLPerf closed, audited · B documented third-party method · C community / review · D vendor-published, not independently verified · E estimate. Power basis: measured with the result · spec vendor spec/envelope · power n/a not published.

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.