FocsleFocsle
UL

YOLO26-Nano

6%
by Ultralytics

Tiny variant tuned for sub-watt accelerators. Where the Coral TPU still earns its place.

Object detectionMITINT8INT4cocotinylow-power
1.2M downloads 71K deploymentsUpdated Mar 22, 2028
Headline:4.8ms · Google Coral Edge TPU · INT8

About this model

Tiny variant tuned for sub-watt accelerators. Where the Coral TPU still earns its place.

Authored by ultralytics. Curated into the Fo’c’sle reference set on 2028-03-22. All cross-chip benchmarks below were collected in matched-pair runs in the HIL lab using the same input pipeline, same upstream preprocessing, and the same downstream consumer. See the methodology page for the full protocol.

Task
Object detection
Parameters
3.2 M
Benchmarked on
9 chips
Deployments
71K

Architecture

Detection backbone + neck + head
Inferred from upstream weights · simplified
ImageCSPDarknet53PANet neckCls headBox headObj headNMS · DFL

Headline benchmarks

Training data

Pretrained on the upstream maintainer’s released checkpoint. Edge-distillation pass uses 2.4M frames from the Fo’c’sle distillation corpus (consented public data + opt-in publisher contributions). Quantization-aware fine-tune uses 320K calibration samples drawn from the target task’s eval domain.

  • Pretraining corpus: upstream maintainer release
  • Distillation corpus: 2,400,000 frames
  • Calibration set: 320,000 samples (per task)
  • Eval set: standard benchmark + matched-pair HIL runs