HWBench

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) vs Hailo-8L (M.2/PCIe, x86 host)

Hailo-8L M.2 module from the Raspberry Pi AI Kit, mounted on the Raspberry Pi M.2 HAT+
Hailo-8L M.2 AI accelerator module (from the Raspberry Pi AI Kit). Photo: SparkFun Electronics, CC BY 2.0, via Wikimedia Commons.
Showing the newest results per platform and source. 18 superseded older results are hidden.Showing all results, including 18 superseded by newer results from the same source.

Hailo-8L (M.2/PCIe, x86 host) is faster in the only like-for-like comparison (largest gap: semantic segmentation, 3.74×).

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only)Hailo-8L (M.2/PCIe, x86 host)
Best semantic segmentation5.24 FPS D
Older data (2020)
191 FPS D
2026-10-15 (page last edited)
Powern/a1.50 W spec
Perf / Wn/a127 FPS/W spec
Pricen/an/a
Workloads with data1 of 76 of 7

Best published semantic segmentation 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

Only Hailo-8L (M.2/PCIe, x86 host) has published object detection results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)201 FPS
throughput · b=1
yolov8n
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n)
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only):

◌

No published object detection results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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.

instance segmentation

Only Hailo-8L (M.2/PCIe, x86 host) has published instance segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)52.90 FPS
throughput · b=1
yolov5m_seg
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m)
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only):

◌

No published instance segmentation results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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-8L (M.2/PCIe, x86 host) has published pose estimation results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)795 FPS
throughput · b=1
mspn_regnetx_800mf
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mid-size CNN
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only):

◌

No published pose estimation results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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

Only Hailo-8L (M.2/PCIe, x86 host) has published image classification results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)1738 FPS
throughput · b=1
mobilenet_v2_1.0
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mobile-class CNN
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only):

◌

No published image classification results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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.

semantic segmentation

✓ Like-for-like: model-size class mid-size CNN, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)19.60 FPS
throughput · b=1
fcn8_resnet_v1_18
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mid-size CNN
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)
Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) CPU-only5.24 FPS
inference_time · b=1
Unet Mv2 (128x128)
TFLite on CPU · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mid-size CNN
Dunknown power n/a
no power published
Google Coral Edge TPU benchmarks page (Table 1)
Older data (2020)

speech-to-text

Only Hailo-8L (M.2/PCIe, x86 host) has published speech-to-text results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)41.80 FPS
throughput · b=1
whisper_base_5s_no_kqs_decoder
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · Whisper base
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only):

◌

No published speech-to-text results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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.

LLM generation

◌

No published LLM generation results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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.

Hailo-8L (M.2/PCIe, x86 host) is faster in all 3 like-for-like comparisons (largest gap: image classification, 242×).

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only)Hailo-8L (M.2/PCIe, x86 host)
Best image classification8.20 FPS D
Older data (2019)
1738 FPS D
2026-10-15 (page last edited)
Powern/a1.50 W spec
Perf / Wn/a1159 FPS/W spec
Pricen/an/a
Workloads with data3 of 76 of 7

Best published image classification 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

⚠ MIXED COMPARISON — not like-for-like. Baseline nano (YOLO-n) at batch 1. Differs: model-size class mobile-class CNN vs nano (YOLO-n).
PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)201 FPS
throughput · b=1
yolov8n
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n)
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)
Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) CPU-only
MIXED: model-size class mobile-class CNN vs nano (YOLO-n)
3.55 FPS
inference_time · b=1
MobileNet v2 SSD (224x224)
TFLite on CPU · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mobile-class CNN
Dunknown power n/a
no power published
Google Coral Edge TPU benchmarks page (Table 1)
Older data (2019)

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

instance segmentation

Only Hailo-8L (M.2/PCIe, x86 host) has published instance segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)52.90 FPS
throughput · b=1
yolov5m_seg
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m)
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only):

◌

No published instance segmentation results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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-8L (M.2/PCIe, x86 host) has published pose estimation results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)795 FPS
throughput · b=1
mspn_regnetx_800mf
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mid-size CNN
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only):

◌

No published pose estimation results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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

✓ Like-for-like: model-size class mobile-class CNN, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)1738 FPS
throughput · b=1
mobilenet_v2_1.0
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mobile-class CNN
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)
Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) CPU-only8.20 FPS
inference_time · b=1
MobileNet v2 (224x224)
TFLite on CPU · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mobile-class CNN
Dunknown power n/a
no power published
Google Coral Edge TPU benchmarks page (Table 1)
Older data (2019)
✓ Like-for-like: model-size class mid-size CNN, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)138 FPS
throughput · b=1
resnet_v1_50
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mid-size CNN
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)
Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) CPU-only0.570 FPS
inference_time · b=1
ResNet-50 V1 (299x299)
TFLite on CPU · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mid-size CNN
Dunknown power n/a
no power published
Google Coral Edge TPU benchmarks page (Table 1)
Older data (2019)

semantic segmentation

✓ Like-for-like: model-size class mid-size CNN, batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)19.60 FPS
throughput · b=1
fcn8_resnet_v1_18
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mid-size CNN
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)
Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) CPU-only5.24 FPS
inference_time · b=1
Unet Mv2 (128x128)
TFLite on CPU · TensorFlow Lite C++ benchmark (Edge TPU runtime) · mid-size CNN
Dunknown power n/a
no power published
Google Coral Edge TPU benchmarks page (Table 1)
Older data (2020)

speech-to-text

Only Hailo-8L (M.2/PCIe, x86 host) has published speech-to-text results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8L (M.2/PCIe, x86 host)41.80 FPS
throughput · b=1
whisper_base_5s_no_kqs_decoder
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · Whisper base
D1.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8L)
2026-10-15 (page last edited)

Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only):

◌

No published speech-to-text results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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.

LLM generation

◌

No published LLM generation results for Coral Dev Board CPU (quad Cortex-A53 @1.5 GHz, CPU only) or Hailo-8L (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.

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.