Hailo-8 M.2 module: edge AI benchmarks
- Independent test Mario Bergeron
Key results
How to read power: results are compared only within the same model. By efficiency ranks only results whose source publishes a power figure; By speed ranks every result. Measured = measured for this workload. Vendor-measured (typical/avg) = the vendor’s own measurement at typical or average load, not an independent test and not a maximum, so fps/W looks better than at max TDP. Chip, Module or Board TDP = the vendor’s published maximum, not measured. Typical power, not max TDP = only a typical figure is published, so fps/W looks better than at full load. Scope says what the watts cover: Accelerator only (host not included), Module, or Whole system. Max of range = top of a published range, so fps/W is a floor (≥). “— not published” = the source gives no power; we never estimate one.
| Workload | Model · precision | Result | Power | Perf/W | Rank on this model | Grade · date | Source |
|---|---|---|---|---|---|---|---|
| image classification | ResNet-50INT8 (vendor quantized) · batch unknown | 1371 FPS | 4.00 WModule Measured | 343● Measured · Module | not in the default fps/W ranking #14 of 50 by speed | C 2026-05-05 (published) | Mario Bergeron, Edge AI Power BenchmarkingMario Bergeron, Edge AI Power Benchmarking (edge-ai-power-p03-ina228), 2026-05-05 |
Ranks compare this board only with boards running the same model. Up to three models per workload; open a rank to see the full same-model table.
Show data — per-workload tables
object detection
No published object detection results for Hailo-8 M.2 module yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
instance segmentation
No published instance segmentation results for Hailo-8 M.2 module yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
pose estimation
No published pose estimation results for Hailo-8 M.2 module 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 group | Best result | Model · precision · stack | Grade | Power | Source · date | Rank in group |
|---|---|---|---|---|---|---|
| mid-size CNN · b=unknown | 1371 FPS | ResNet-50 INT8 (vendor quantized) · vendor SDK (see source) | C | 4.00 W ● Measured, Module | Mario Bergeron, Edge AI Power Benchmarking 2026-05-05 (published) | 23 of 47 |
semantic segmentation
No published semantic segmentation results for Hailo-8 M.2 module 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
No published speech-to-text results for Hailo-8 M.2 module 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-8 M.2 module yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.
Grades: A audited MLPerf · B third-party · C community · D vendor. How we rank · JSON