FocsleFo’c’sle
TA

YOLO-World-Edge

14%
by Tencent ARC

Open-vocabulary detector. Text-prompt the classes at runtime; no retraining.

Object detectionApache-2.0INT8FP16open-vocabzero-shot
96K downloads 4.1K deploymentsUpdated Mar 16, 2028
Headline:21.4ms · NVIDIA Jetson Orin Nano · INT8
OverviewBenchmarks6Sim ResultsDeploy6FilesDiscussion23

Deploy YOLO-World-Edge

Pick a chip family. We hand you the artifacts (HEF, TRT engine, Core ML, ONNX) plus a one-click endpoint deploy. For private endpoints, on-prem deploy, or air-gapped distribution, see Enterprise.

NNVIDIA Jetson Orin Nano
# Build a TensorRT engine
$ focsle pull tencent-arc/yolo-world-edge --target jetson-orin-nano
$ focsle build trt --plan yolo-world-edge.plan \
    --precision fp16 \
    --workspace 4G

# Run with TensorRT
import focsle.runtime as fr
m = fr.load("yolo-world-edge.plan", target="trt")
out = m.run(frame)

One-click endpoint

Spins up a managed endpoint in the closest region. Pro and above.

Or deploy yourself