medical segmentation benchmarks on edge AI hardware

6 published rows. Each table compares only results with the same model-size class and batch size. Search this workload · JSON.

Showing the newest results per platform and source. 2 superseded older results are hidden.Showing all results, including 2 superseded by newer results from the same source.

Fastest in the best-covered like-for-like group (mid-size CNN, batch unknown): Lenovo ThinkEdge SE455i V3 (2x NVIDIA L4-PCIe-24GB) at 2.19 FPS A 2026-04-01 (published). 1 groups, 3 platforms.

Show data — 1 like-for-like tables

mid-size CNN · batch unknown (3 platforms)

✓ Like-for-like: model-size class mid-size CNN, batch unknown (size or batch not stated by source — unverified). Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
Lenovo ThinkEdge SE455i V3 (2x NVIDIA L4-PCIe-24GB)	2.19 FPS throughput_offline · b=unknown	MLPerf 3d-unet-99 int8 · TensorRT 10.8, CUDA 13.1 · mid-size CNN	A	unknown power n/a no power published	MLPerf Inference v6.0, closed division, edge suite 2026-04-01 (published)
NVIDIA Jetson Orin NX 16GB	0.200 FPS throughput_offline · b=unknown	MLPerf 3D-Unet-99.0 INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN	D	unknown power n/a no power published	NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) Older data (2023)
NVIDIA Jetson Orin NX 16GB (MaxQ)	0.190 FPS throughput_offline · b=unknown	MLPerf 3D-Unet-99.0 INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN	D	22.04 W measured reported in result source — measured	NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) Older data (2023)

Fastest in the best-covered like-for-like group (mid-size CNN, batch unknown): Lenovo ThinkEdge SE455i V3 (2x NVIDIA L4-PCIe-24GB) at 2.19 FPS A 2026-04-01 (published). 1 groups, 4 platforms.

Show data — 1 like-for-like tables

mid-size CNN · batch unknown (4 platforms)

✓ Like-for-like: model-size class mid-size CNN, batch unknown (size or batch not stated by source — unverified). Model, precision and stack may still differ.

Platform	Result	Model · precision · stack	Grade	Power	Source
Lenovo ThinkEdge SE455i V3 (2x NVIDIA L4-PCIe-24GB)	2.19 FPS throughput_offline · b=unknown	MLPerf 3d-unet-99 int8 · TensorRT 10.8, CUDA 13.1 · mid-size CNN	A	unknown power n/a no power published	MLPerf Inference v6.0, closed division, edge suite 2026-04-01 (published)
NVIDIA Jetson AGX Orin 64GB	0.510 FPS throughput_offline · b=unknown	MLPerf 3D-Unet-99.0 INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN	D	65.00 W spec platform spec envelope (not measured with this result)	NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) Older data (2023)
NVIDIA Jetson Orin NX 16GB	0.200 FPS throughput_offline · b=unknown	MLPerf 3D-Unet-99.0 INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN	D	unknown power n/a no power published	NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) Older data (2023)
NVIDIA Jetson Orin NX 16GB (MaxQ)	0.190 FPS throughput_offline · b=unknown	MLPerf 3D-Unet-99.0 INT8/FP16 (MLPerf closed) · TensorRT (MLPerf Inference, older round) · mid-size CNN	D	22.04 W measured reported in result source — measured	NVIDIA Jetson Benchmarks (MLPerf v3.1 results table) Older data (2023)

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.