HWBenchedge-AI hardware data, cited & graded

Hailo-8 (M.2/PCIe, x86 host) vs HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition)

HailoAI accelerator (M.2) · no photo yet
No licensed photo available — placeholder drawing.
HPEdatacenter server · no photo yet
No licensed photo available — placeholder drawing.

No like-for-like comparison yet: both have published results, but model size or batch differ. Treat the numbers below as indicative only.

Hailo-8 (M.2/PCIe, x86 host)HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition)
Best speech-to-text310 FPS D
undated
9228 FPS A
undated
Power2.50 W specn/a
Perf / W124 FPS/W specn/a
Pricen/an/a
Workloads with data6 of 71 of 7

Best published speech-to-text result per platform. n/a = not published; never estimated.

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

object detection

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

PlatformResultModel · precision · stackGradePowerSource
Hailo-8 (M.2/PCIe, x86 host)1036 FPS
throughput · b=1
yolov8n
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n)
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8)
undated

HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition):

◌

No published object detection results for HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition) or Hailo-8 (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-8 (M.2/PCIe, x86 host) has published instance segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8 (M.2/PCIe, x86 host)68.70 FPS
throughput · b=1
yolov5m_seg
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m)
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8)
undated

HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition):

◌

No published instance segmentation results for HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition) or Hailo-8 (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-8 (M.2/PCIe, x86 host) has published pose estimation results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8 (M.2/PCIe, x86 host)68.60 FPS
throughput · b=1
yolov8m_pose
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m)
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8)
undated

HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition):

◌

No published pose estimation results for HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition) or Hailo-8 (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-8 (M.2/PCIe, x86 host) has published image classification results.

PlatformResultModel · precision · stackGradePowerSource
Hailo-8 (M.2/PCIe, x86 host)2597 FPS
throughput · b=1
mobilenet_v2_1.0
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mobile-class CNN
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8)
undated

HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition):

◌

No published image classification results for HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition) or Hailo-8 (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

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

PlatformResultModel · precision · stackGradePowerSource
Hailo-8 (M.2/PCIe, x86 host)42.60 FPS
throughput · b=1
fcn8_resnet_v1_18
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mid-size CNN
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8)
undated

HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition):

◌

No published semantic segmentation results for HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition) or Hailo-8 (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.

speech-to-text

⚠ MIXED COMPARISON — not like-for-like. Baseline Whisper base at batch 1. Differs: model-size class unknown vs Whisper base; batch unknown vs 1.
PlatformResultModel · precision · stackGradePowerSource
Hailo-8 (M.2/PCIe, x86 host)51.40 FPS
throughput · b=1
whisper_base_5s_encoder
INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · Whisper base
D2.50 W spec
reported in result source — spec
Hailo Model Zoo public models (Hailo-8)
undated
HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition)
MIXED: model-size class unknown vs Whisper base; batch unknown vs 1
9228 FPS
throughput_offline · b=unknown
MLPerf whisper
fp4 · TensorRT 10.14.1.48, CUDA 13.0 · unknown
Aunknown power n/a
no power published
MLPerf Inference v6.0 (closed, datacenter) ID 6.0-0054
undated

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

LLM generation

◌

No published LLM generation results for Hailo-8 (M.2/PCIe, x86 host) or HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition) 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.