A model is still running

A model is still running or downloading. Leaving will stop the current operation. Stay on this page to let it finish.

Skip to content
LocalAI.toolsBeta

Join the waitlist

Get an email when the new apps and model runs launch.

No account needed.

YOLOX-M — LiteRT Object Detection

Find common objects such as people, vehicles, and animals in a still image. Returns labels, confidence scores, and boxes for 80 COCO categories; it does not search arbitrary text descriptions.

Browser inferencePowered by WebAI · Private · Unlimited runs
About this model

Find common objects such as people, vehicles, and animals in a still image. Returns labels, confidence scores, and boxes for 80 COCO categories; it does not search arbitrary text descriptions.

Created by
Megvii
License
Apache-2.0
Model released
Unknown
Source repository created
Jul 17, 2021
Model weights · FP16
51.0 MB

Best for

  • Finding common COCO objects in photographs.
  • Prototyping local object-detection interfaces.

Keep in mind

  • Only the 80 COCO categories are recognized.
  • Small, crowded, occluded, blurred, or unusual objects can be missed or mislabeled.
  • Bounding boxes and confidence scores are estimates and must not drive safety-critical decisions.

Processed on your deviceInference runs in this browser. Input/output sharing requires consent for each run. Basic run logs include device information and approximate connection location. Model and runtime files download from external hosts. Saved downloads may be cleared by your browser.

Sources & technical details
Original model
Megvii-BaseDetection/YOLOX
Release verification
Unknown
Release evidence
Exact original checkpoint public release date has not been verified. Repository creation, training, paper, artifact conversion and update dates are not release evidence.
Source updated
Apr 19, 2023
Browser model files
litert-community/yolox-m-litert
Files updated
Sep 6, 2026
Artifact revision
f092a1457c4c39ca924f8815df2a42fe51bfb85e

Input

IMAGE

Sample result

YOLOX-M — LiteRT Object Detection

Settings

Caps the number of detections returned. Lower values reduce result size and may omit real objects. Higher values allow more boxes in crowded scenes and increase output and postprocessing work.
Adds a self-contained SVG presentation image alongside the unchanged native model fields. When enabled, draws model predictions or presents generated media and text. Adds CPU postprocessing time and image bytes. It does not change model predictions.
Advanced settings 2
Sets the minimum score for returned object detections. Lower values retain more weak detections and false positives. Higher values return fewer, stronger detections but may miss small or obscured objects.
Sets the overlap cutoff for suppressing duplicate detection boxes. Lower values suppress overlapping boxes more aggressively and can remove nearby subjects. Higher values retain more overlapping boxes, including duplicates.

Output

Your result will appear here

Add input or try the sample, then run the model.

Benchmark evidence

Saved worker evidence is separate from benchmarks run on your device. It does not guarantee speed or quality on every browser.

YOLOX-M — LiteRT Object Detection

2 configurations tested
Passed2
Failed0
TestedSep 8, 2026
RuntimeLiteRT.js 2.5.3

Quality criteria

No explicit quality gate recorded. Review per-case evidence; full certification is pending.

PrecisionDeviceResult
FP16GPU · WebGPUAcceleratedPassedModerate
FP16CPU · WASMPassedVery slow
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-09-08T18:10:00.000Z
Environment
Headless Chrome 151 on macOS; LiteRT.js 2.5.3
Runtime
LiteRT.js 2.5.3
Artifact revision
f092a1457c4c39ca924f8815df2a42fe51bfb85e
Fixture
{
  "file": "modnet-portrait-pexels-5965592.jpg",
  "url": "https://f005.backblazeb2.com/file/hubters-webai-public/assets/benchmarks/modnet-portrait-pexels-5965592.jpg",
  "size": 78124,
  "sha1": "38212739a4a4f0be25d84863cf991d7fb6c6d818",
  "width": 1024,
  "height": 683,
  "license": "Pexels License"
}
Rerun when
model artifact revision change; LiteRT.js version change; fixture or quality-gate change; browser/backend behavior change
Per-case quality & failure details
[
  {
    "precision": "fp16",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "grade": "reference",
      "label": "person",
      "score": 0.939385
    },
    "runtime": {
      "loadMs": 10978.9,
      "inferenceMs": 5773.8,
      "totalMs": 16752.7,
      "grade": "very-slow"
    }
  },
  {
    "precision": "fp16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "grade": "excellent",
      "label": "person",
      "scoreDifference": 0.000001,
      "maximumBoxDifference": 0.000001
    },
    "runtime": {
      "loadMs": 11170.9,
      "inferenceMs": 892.1,
      "totalMs": 12063,
      "grade": "slow"
    }
  }
]

Something not quite right?

Tell us what happened with YOLOX. Loading, results, or the page itself—we’re here for all of it.

Attachments Optional

Up to 3 files · 50 MB each

Browser, OS, CPU/GPU, memory, screen, storage, and network details are included automatically. Model inputs, results, and browsing history are not collected.