FocsleFo’c’sle
UL

YOLO27-Edge

18%
by Ultralytics

Ninth-generation YOLO with edge-first quantization recipe. The default workhorse for 1080p multi-stream perception.

Object detectionMITINT8INT4FP16cocoedgereal-time
487K downloads 38K deploymentsUpdated Apr 11, 2028
Headline:14.2ms · Hailo-8 · INT8
arXiv GitHub
OverviewBenchmarks11Sim ResultsDeploy11FilesDiscussion23

Deploy YOLO27-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.

HHailo-8
# Compile to Hailo HEF
$ pip install focsle
$ focsle pull ultralytics/yolo27-edge --target hailo-8
$ focsle compile yolo27-edge.onnx --target hailo-8 --quant int8

# Run on-device (HailoRT)
import focsle.runtime as fr
m = fr.load("yolo27-edge.hef", target="hailo")
out = m.run(frame)

One-click endpoint

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

Or deploy yourself