Hailo-8L (M.2/PCIe, x86 host) vs Rockchip RK3566/RK3568 (NPU)
.jpg){kind=link}
Rockchipedge SoCNo licensed photo yet
Hailo-8L (M.2/PCIe, x86 host) is faster in all 9 like-for-like comparisons (largest gap: image classification, 9.04×).
| Hailo-8L (M.2/PCIe, x86 host) | Rockchip RK3566/RK3568 (NPU) | |
|---|---|---|
| Best object detection | 437 FPS D 2026-10-15 (page last edited) | 49.90 FPS C 2026-10-13 (page last edited) |
| Power | 1.50 W spec | n/a |
| Perf / W | 291 FPS/W spec | n/a |
| Price | n/a | n/a |
| Workloads with data | 6 of 7 | 5 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.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| 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) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 49.90 FPS throughput · b=1 | yolov6n INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · nano (YOLO-n) | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
✓ Like-for-like: model-size class small (YOLO-s), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8L (M.2/PCIe, x86 host) | 137 FPS throughput · b=1 | yolov5s_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · small (YOLO-s) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 27.10 FPS throughput · b=1 | yolov5s_relu INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · small (YOLO-s) | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
✓ Like-for-like: model-size class medium (YOLO-m), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8L (M.2/PCIe, x86 host) | 62.90 FPS throughput · b=1 | yolov5m_wo_spp INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · medium (YOLO-m) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 8.70 FPS throughput · b=1 | yolov5m INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · medium (YOLO-m) | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
instance segmentation
✓ Like-for-like: model-size class medium (YOLO-m), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| 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) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 6.80 FPS throughput · b=1 | yolov5m-seg INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · medium (YOLO-m) | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
✓ Like-for-like: model-size class nano (YOLO-n), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8L (M.2/PCIe, x86 host) | 168 FPS throughput · b=1 | yolov8n_seg INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · nano (YOLO-n) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 34.40 FPS throughput · b=1 | yolov5n-seg INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · nano (YOLO-n) | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
✓ Like-for-like: model-size class small (YOLO-s), batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8L (M.2/PCIe, x86 host) | 101 FPS throughput · b=1 | yolov5s_seg INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · small (YOLO-s) | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 15.50 FPS throughput · b=1 | yolov5s-seg INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · small (YOLO-s) | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
pose estimation
⚠ MIXED COMPARISON — not like-for-like. Baseline mid-size CNN at batch 1. Differs: model-size class nano (YOLO-n) vs mid-size CNN.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| 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 | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) MIXED: model-size class nano (YOLO-n) vs mid-size CNN | 23.70 FPS throughput · b=1 | yolov8n-pose INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · nano (YOLO-n) | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
No shared like-for-like group exists for this pair.
image classification
✓ Like-for-like: model-size class mobile-class CNN, batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| 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 | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 192 FPS throughput · b=1 | mobilenetv2-12 INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mobile-class CNN | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
✓ Like-for-like: model-size class mid-size CNN, batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| 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 | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 38.60 FPS throughput · b=1 | resnet50-v2-7 INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mid-size CNN | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
semantic segmentation
✓ Like-for-like: model-size class mobile-class CNN, batch 1. Model, precision and stack may still differ.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| Hailo-8L (M.2/PCIe, x86 host) | 99.10 FPS throughput · b=1 | unet_mobilenet_v2 INT8 (Hailo quantized) · Hailo DFC v2.20.0 / HailoRT (model zoo) · mobile-class CNN | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
| Rockchip RK3566/RK3568 (NPU) | 11.70 FPS throughput · b=1 | deeplab-v3-plus-mobilenet-v2 INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mobile-class CNN | C | unknown power n/a no power published | Rockchip rknn_model_zoo README benchmark table 2026-10-13 (page last edited) |
speech-to-text
Only Hailo-8L (M.2/PCIe, x86 host) has published speech-to-text results.
| Platform | Result | Model · precision · stack | Grade | Power | Source |
|---|---|---|---|---|---|
| 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 | D | 1.50 W spec reported in result source — spec | Hailo Model Zoo public models (Hailo-8L) 2026-10-15 (page last edited) |
Rockchip RK3566/RK3568 (NPU):
◌
No published speech-to-text results for Rockchip RK3566/RK3568 (NPU) 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 Hailo-8L (M.2/PCIe, x86 host) or Rockchip RK3566/RK3568 (NPU) 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.