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.

RF-DETR Base 2

Detect common COCO objects with labels, scores and original-image bounding boxes.

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

Detect common COCO objects with labels, scores and original-image bounding boxes.

Created by
Roboflow
License
Apache-2.0
Model released
Unknown
Source repository created
May 11, 2026
Model weights · FP32
109.2 MB

Best for

  • Review common objects and their spatial locations in photos.

Keep in mind

  • English COCO labels and controlled dog, person and blank fixtures. Small or occluded objects may be missed.
  • Confidence is not a correctness guarantee. Review outputs before using them in high-impact decisions.
  • Accepts one still PNG or JPEG up to 20 MB and 20 megapixels. EXIF orientation is applied.
  • The runtime returns complete spatial predictions after one forward pass. Windows and Intel Mac are unverified.

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
https://huggingface.co/Roboflow/rf-detr-base-2
Release verification
Unknown
Release evidence
Exact original checkpoint release date is distinct from the Transformers repository creation date.
Source updated
May 20, 2026
Browser model files
https://assets.localai.tools/models/converted/v1/rf-detr-base-2/313a58bf1ea35df61b56af526240848d1b11d68c/
Files updated
Nov 14, 2026
Artifact revision
313a58bf1ea35df61b56af526240848d1b11d68c

Input

IMAGE

Sample result

RF-DETR Base 2

Settings

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 1
Sets the cutoff used to keep a prediction or create a hard mask. Lower values keep more weak predictions or foreground pixels, with more possible false positives. Higher values are stricter and may miss details. Automatic/null preserves soft alpha edges when offered.

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.

RF-DETR Base 2

6 configurations tested
Passed6
Failed0
TestedNov 14, 2026
RuntimeTransformers.js 4.3.2

Quality criteria

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

PrecisionDeviceResult
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedFast
FP32CPU · WASMPassedSlow
FP32CPU · WASMPassedSlow
FP32CPU · WASMPassedSlow
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-14T18:09:21.899Z
Environment
Not recorded
Runtime
Transformers.js 4.3.2
Artifact revision
313a58bf1ea35df61b56af526240848d1b11d68c
Fixture
{
  "file": "model-samples/desktop/mobilenet-dog.jpg",
  "size": 83281,
  "sha1": "f1d042827c2f2154a6d8043b8e8f07c1be612941",
  "sha256": "d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1",
  "url": "https://assets.localai.tools/samples/v1/files/d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1/mobilenet-dog.jpg"
}
Rerun when
Artifact revision; Runtime version; Fixture or quality gate; Browser backend
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9859160397961659,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 2163.7000000476837,
      "loadMs": 4184.600000023842,
      "totalMs": 6348.300000071526,
      "grade": "usable",
      "imagesPerSecond": 0.4621712806664334,
      "version": "4.3.2",
      "artifactRevision": "313a58bf1ea35df61b56af526240848d1b11d68c",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8591648689777421,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 2067.100000023842,
      "loadMs": 4184.600000023842,
      "totalMs": 6251.700000047684,
      "grade": "usable",
      "imagesPerSecond": 0.4837695321892826,
      "version": "4.3.2",
      "artifactRevision": "313a58bf1ea35df61b56af526240848d1b11d68c",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 2076.5,
      "loadMs": 4184.600000023842,
      "totalMs": 6261.100000023842,
      "grade": "usable",
      "imagesPerSecond": 0.4815795810257645,
      "version": "4.3.2",
      "artifactRevision": "313a58bf1ea35df61b56af526240848d1b11d68c",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9859160397961659,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 129.70000004768372,
      "loadMs": 3357.199999988079,
      "totalMs": 3486.900000035763,
      "grade": "fast",
      "imagesPerSecond": 7.710100228468417,
      "version": "4.3.2",
      "artifactRevision": "313a58bf1ea35df61b56af526240848d1b11d68c",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 35
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8591648689777421,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 64.89999997615814,
      "loadMs": 3357.199999988079,
      "totalMs": 3422.099999964237,
      "grade": "fast",
      "imagesPerSecond": 15.408320498726702,
      "version": "4.3.2",
      "artifactRevision": "313a58bf1ea35df61b56af526240848d1b11d68c",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 35
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 60.799999952316284,
      "loadMs": 3357.199999988079,
      "totalMs": 3417.9999999403954,
      "grade": "fast",
      "imagesPerSecond": 16.447368433951837,
      "version": "4.3.2",
      "artifactRevision": "313a58bf1ea35df61b56af526240848d1b11d68c",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 35
    }
  }
]

RF-DETR Base

6 configurations tested
Passed6
Failed0
TestedNov 14, 2026
RuntimeTransformers.js 4.3.2

Quality criteria

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

PrecisionDeviceResult
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedFast
FP32CPU · WASMPassedSlow
FP32CPU · WASMPassedSlow
FP32CPU · WASMPassedSlow
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-14T18:09:07.309Z
Environment
Not recorded
Runtime
Transformers.js 4.3.2
Artifact revision
a3b51d56717412d92cd3034b155750c1c9d48dfe
Fixture
{
  "file": "model-samples/desktop/mobilenet-dog.jpg",
  "size": 83281,
  "sha1": "f1d042827c2f2154a6d8043b8e8f07c1be612941",
  "sha256": "d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1",
  "url": "https://assets.localai.tools/samples/v1/files/d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1/mobilenet-dog.jpg"
}
Rerun when
Artifact revision; Runtime version; Fixture or quality gate; Browser backend
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.982345368327759,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 2120.899999976158,
      "loadMs": 4508.800000011921,
      "totalMs": 6629.699999988079,
      "grade": "usable",
      "imagesPerSecond": 0.4714979489892222,
      "version": "4.3.2",
      "artifactRevision": "a3b51d56717412d92cd3034b155750c1c9d48dfe",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8383618455158113,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 2087.600000023842,
      "loadMs": 4508.800000011921,
      "totalMs": 6596.400000035763,
      "grade": "usable",
      "imagesPerSecond": 0.47901896914570763,
      "version": "4.3.2",
      "artifactRevision": "a3b51d56717412d92cd3034b155750c1c9d48dfe",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 2042.0999999642372,
      "loadMs": 4508.800000011921,
      "totalMs": 6550.899999976158,
      "grade": "usable",
      "imagesPerSecond": 0.489691983750802,
      "version": "4.3.2",
      "artifactRevision": "a3b51d56717412d92cd3034b155750c1c9d48dfe",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.982345368327759,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 193.5,
      "loadMs": 3443.300000011921,
      "totalMs": 3636.800000011921,
      "grade": "fast",
      "imagesPerSecond": 5.167958656330749,
      "version": "4.3.2",
      "artifactRevision": "a3b51d56717412d92cd3034b155750c1c9d48dfe",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 35
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8383618455158113,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 70.90000003576279,
      "loadMs": 3443.300000011921,
      "totalMs": 3514.2000000476837,
      "grade": "fast",
      "imagesPerSecond": 14.104372348315774,
      "version": "4.3.2",
      "artifactRevision": "a3b51d56717412d92cd3034b155750c1c9d48dfe",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 35
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 64.80000001192093,
      "loadMs": 3443.300000011921,
      "totalMs": 3508.100000023842,
      "grade": "fast",
      "imagesPerSecond": 15.432098762593133,
      "version": "4.3.2",
      "artifactRevision": "a3b51d56717412d92cd3034b155750c1c9d48dfe",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 35
    }
  }
]

RF-DETR Large

6 configurations tested
Passed6
Failed0
TestedNov 14, 2026
RuntimeTransformers.js 4.3.2

Quality criteria

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

PrecisionDeviceResult
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedFast
FP32CPU · WASMPassedSlow
FP32CPU · WASMPassedSlow
FP32CPU · WASMPassedSlow
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-14T18:08:50.747Z
Environment
Not recorded
Runtime
Transformers.js 4.3.2
Artifact revision
42504c3feaf6925cab7f8ab176590d4248788320
Fixture
{
  "file": "model-samples/desktop/mobilenet-dog.jpg",
  "size": 83281,
  "sha1": "f1d042827c2f2154a6d8043b8e8f07c1be612941",
  "sha256": "d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1",
  "url": "https://assets.localai.tools/samples/v1/files/d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1/mobilenet-dog.jpg"
}
Rerun when
Artifact revision; Runtime version; Fixture or quality gate; Browser backend
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9785894936000155,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 3008,
      "loadMs": 3927,
      "totalMs": 6935,
      "grade": "usable",
      "imagesPerSecond": 0.3324468085106383,
      "version": "4.3.2",
      "artifactRevision": "42504c3feaf6925cab7f8ab176590d4248788320",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8425224502081975,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 2959.199999988079,
      "loadMs": 3927,
      "totalMs": 6886.199999988079,
      "grade": "usable",
      "imagesPerSecond": 0.3379291700473197,
      "version": "4.3.2",
      "artifactRevision": "42504c3feaf6925cab7f8ab176590d4248788320",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 3015.699999988079,
      "loadMs": 3927,
      "totalMs": 6942.699999988079,
      "grade": "usable",
      "imagesPerSecond": 0.3315979706217306,
      "version": "4.3.2",
      "artifactRevision": "42504c3feaf6925cab7f8ab176590d4248788320",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9785894936000155,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 347.19999998807907,
      "loadMs": 4959,
      "totalMs": 5306.199999988079,
      "grade": "fast",
      "imagesPerSecond": 2.8801843318961247,
      "version": "4.3.2",
      "artifactRevision": "42504c3feaf6925cab7f8ab176590d4248788320",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 39
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8425224502081975,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 93.20000004768372,
      "loadMs": 4959,
      "totalMs": 5052.200000047684,
      "grade": "fast",
      "imagesPerSecond": 10.72961372841601,
      "version": "4.3.2",
      "artifactRevision": "42504c3feaf6925cab7f8ab176590d4248788320",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 39
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 89,
      "loadMs": 4959,
      "totalMs": 5048,
      "grade": "fast",
      "imagesPerSecond": 11.235955056179776,
      "version": "4.3.2",
      "artifactRevision": "42504c3feaf6925cab7f8ab176590d4248788320",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 39
    }
  }
]

RF-DETR Medium

6 configurations tested
Passed6
Failed0
TestedNov 14, 2026
RuntimeTransformers.js 4.3.2

Quality criteria

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

PrecisionDeviceResult
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedFast
FP32CPU · WASMPassedModerate
FP32CPU · WASMPassedModerate
FP32CPU · WASMPassedModerate
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-14T18:09:57.541Z
Environment
Not recorded
Runtime
Transformers.js 4.3.2
Artifact revision
5322a40cf0bad4165a91a5a9d537273dc82c0d29
Fixture
{
  "file": "model-samples/desktop/mobilenet-dog.jpg",
  "size": 83281,
  "sha1": "f1d042827c2f2154a6d8043b8e8f07c1be612941",
  "sha256": "d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1",
  "url": "https://assets.localai.tools/samples/v1/files/d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1/mobilenet-dog.jpg"
}
Rerun when
Artifact revision; Runtime version; Fixture or quality gate; Browser backend
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9807309162889363,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 1929.300000011921,
      "loadMs": 2942.2999999523163,
      "totalMs": 4871.599999964237,
      "grade": "usable",
      "imagesPerSecond": 0.5183227077146224,
      "version": "4.3.2",
      "artifactRevision": "5322a40cf0bad4165a91a5a9d537273dc82c0d29",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8368835599257513,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 1885.5,
      "loadMs": 2942.2999999523163,
      "totalMs": 4827.799999952316,
      "grade": "usable",
      "imagesPerSecond": 0.5303632988597189,
      "version": "4.3.2",
      "artifactRevision": "5322a40cf0bad4165a91a5a9d537273dc82c0d29",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 1881.4000000357628,
      "loadMs": 2942.2999999523163,
      "totalMs": 4823.699999988079,
      "grade": "usable",
      "imagesPerSecond": 0.5315190815249237,
      "version": "4.3.2",
      "artifactRevision": "5322a40cf0bad4165a91a5a9d537273dc82c0d29",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9807309162889363,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 154.9000000357628,
      "loadMs": 3104.800000011921,
      "totalMs": 3259.7000000476837,
      "grade": "fast",
      "imagesPerSecond": 6.455777919749021,
      "version": "4.3.2",
      "artifactRevision": "5322a40cf0bad4165a91a5a9d537273dc82c0d29",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 39
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8368835599257513,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 62.60000002384186,
      "loadMs": 3104.800000011921,
      "totalMs": 3167.400000035763,
      "grade": "fast",
      "imagesPerSecond": 15.97444088848466,
      "version": "4.3.2",
      "artifactRevision": "5322a40cf0bad4165a91a5a9d537273dc82c0d29",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 39
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 71.20000004768372,
      "loadMs": 3104.800000011921,
      "totalMs": 3176.0000000596046,
      "grade": "fast",
      "imagesPerSecond": 14.044943810818609,
      "version": "4.3.2",
      "artifactRevision": "5322a40cf0bad4165a91a5a9d537273dc82c0d29",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 39
    }
  }
]

RF-DETR Nano

6 configurations tested
Passed6
Failed0
TestedNov 14, 2026
RuntimeTransformers.js 4.3.2

Quality criteria

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

PrecisionDeviceResult
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedFast
FP32CPU · WASMPassedModerate
FP32CPU · WASMPassedModerate
FP32CPU · WASMPassedModerate
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-14T18:09:32.226Z
Environment
Not recorded
Runtime
Transformers.js 4.3.2
Artifact revision
1aceaeb46494d5d68cf9e7804aa1c25e25bbe2f2
Fixture
{
  "file": "model-samples/desktop/mobilenet-dog.jpg",
  "size": 83281,
  "sha1": "f1d042827c2f2154a6d8043b8e8f07c1be612941",
  "sha256": "d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1",
  "url": "https://assets.localai.tools/samples/v1/files/d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1/mobilenet-dog.jpg"
}
Rerun when
Artifact revision; Runtime version; Fixture or quality gate; Browser backend
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9878251191442965,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 803.9000000357628,
      "loadMs": 4051.099999964237,
      "totalMs": 4855,
      "grade": "usable",
      "imagesPerSecond": 1.2439358128567153,
      "version": "4.3.2",
      "artifactRevision": "1aceaeb46494d5d68cf9e7804aa1c25e25bbe2f2",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8368835599257513,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 771.4000000357628,
      "loadMs": 4051.099999964237,
      "totalMs": 4822.5,
      "grade": "usable",
      "imagesPerSecond": 1.2963443089883837,
      "version": "4.3.2",
      "artifactRevision": "1aceaeb46494d5d68cf9e7804aa1c25e25bbe2f2",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 756.8000000119209,
      "loadMs": 4051.099999964237,
      "totalMs": 4807.899999976158,
      "grade": "usable",
      "imagesPerSecond": 1.3213530655182983,
      "version": "4.3.2",
      "artifactRevision": "1aceaeb46494d5d68cf9e7804aa1c25e25bbe2f2",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9878251191442965,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 137.4000000357628,
      "loadMs": 3846.399999976158,
      "totalMs": 3983.800000011921,
      "grade": "fast",
      "imagesPerSecond": 7.27802037656272,
      "version": "4.3.2",
      "artifactRevision": "1aceaeb46494d5d68cf9e7804aa1c25e25bbe2f2",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 34
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8368835599257513,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 36.19999998807907,
      "loadMs": 3846.399999976158,
      "totalMs": 3882.599999964237,
      "grade": "fast",
      "imagesPerSecond": 27.624309401362083,
      "version": "4.3.2",
      "artifactRevision": "1aceaeb46494d5d68cf9e7804aa1c25e25bbe2f2",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 34
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 29.299999952316284,
      "loadMs": 3846.399999976158,
      "totalMs": 3875.6999999284744,
      "grade": "fast",
      "imagesPerSecond": 34.12969288830821,
      "version": "4.3.2",
      "artifactRevision": "1aceaeb46494d5d68cf9e7804aa1c25e25bbe2f2",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 34
    }
  }
]

RF-DETR Seg Nano Desktop

6 configurations tested
Passed6
Failed0
TestedNov 16, 2026
RuntimeTransformers.js 4.3.2

Quality criteria

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

PrecisionDeviceResult
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedFast
FP32CPU · WASMPassedModerate
FP32CPU · WASMPassedModerate
FP32CPU · WASMPassedModerate
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-16T05:27:59.279Z
Environment
Not recorded
Runtime
Transformers.js 4.3.2
Artifact revision
9e55192d70da87cd00c4b5a227dc69c673d3c93e
Fixture
{
  "file": "model-samples/desktop/mobilenet-dog.jpg",
  "size": 83281,
  "sha1": "f1d042827c2f2154a6d8043b8e8f07c1be612941",
  "sha256": "d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1",
  "url": "https://assets.localai.tools/samples/v1/files/d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1/mobilenet-dog.jpg"
}
Rerun when
Artifact revision; Runtime version; Fixture or quality gate; Browser backend
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9858529664484783,
      "passed": true,
      "pointRecall": 1
    },
    "runtime": {
      "loadMs": 1448.7999999999302,
      "inferenceMs": 1172.5,
      "totalMs": 2621.29999999993,
      "imagesPerSecond": 0.8528784648187633,
      "grade": "usable",
      "version": "4.3.2",
      "artifactRevision": "9e55192d70da87cd00c4b5a227dc69c673d3c93e",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.829411477614624,
      "passed": true,
      "pointRecall": 1
    },
    "runtime": {
      "loadMs": 1448.7999999999302,
      "inferenceMs": 1150.6999999999534,
      "totalMs": 2599.4999999998836,
      "imagesPerSecond": 0.8690362388111936,
      "grade": "usable",
      "version": "4.3.2",
      "artifactRevision": "9e55192d70da87cd00c4b5a227dc69c673d3c93e",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true,
      "pointRecall": 1
    },
    "runtime": {
      "loadMs": 1448.7999999999302,
      "inferenceMs": 1133.1999999999534,
      "totalMs": 2581.9999999998836,
      "imagesPerSecond": 0.882456759618815,
      "grade": "usable",
      "version": "4.3.2",
      "artifactRevision": "9e55192d70da87cd00c4b5a227dc69c673d3c93e",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9858529664484783,
      "passed": true,
      "pointRecall": 1
    },
    "runtime": {
      "loadMs": 1358.4000000000233,
      "inferenceMs": 120.90000000002328,
      "totalMs": 1479.3000000000466,
      "imagesPerSecond": 8.271298593877646,
      "grade": "fast",
      "version": "4.3.2",
      "artifactRevision": "9e55192d70da87cd00c4b5a227dc69c673d3c93e",
      "gpuDispatches": 42
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8294114045024589,
      "passed": true,
      "pointRecall": 1
    },
    "runtime": {
      "loadMs": 1358.4000000000233,
      "inferenceMs": 66.19999999995343,
      "totalMs": 1424.5999999999767,
      "imagesPerSecond": 15.105740181279508,
      "grade": "fast",
      "version": "4.3.2",
      "artifactRevision": "9e55192d70da87cd00c4b5a227dc69c673d3c93e",
      "gpuDispatches": 42
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true,
      "pointRecall": 1
    },
    "runtime": {
      "loadMs": 1358.4000000000233,
      "inferenceMs": 38.199999999953434,
      "totalMs": 1396.5999999999767,
      "imagesPerSecond": 26.1780104712361,
      "grade": "fast",
      "version": "4.3.2",
      "artifactRevision": "9e55192d70da87cd00c4b5a227dc69c673d3c93e",
      "gpuDispatches": 42
    }
  }
]

RF-DETR Small

6 configurations tested
Passed6
Failed0
TestedNov 14, 2026
RuntimeTransformers.js 4.3.2

Quality criteria

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

PrecisionDeviceResult
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedVery fast
FP32GPU · WebGPUAcceleratedPassedFast
FP32CPU · WASMPassedModerate
FP32CPU · WASMPassedModerate
FP32CPU · WASMPassedModerate
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-14T18:09:45.554Z
Environment
Not recorded
Runtime
Transformers.js 4.3.2
Artifact revision
a1308f1b8cdb1ec5ed5b32424d03b09e8d207a59
Fixture
{
  "file": "model-samples/desktop/mobilenet-dog.jpg",
  "size": 83281,
  "sha1": "f1d042827c2f2154a6d8043b8e8f07c1be612941",
  "sha256": "d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1",
  "url": "https://assets.localai.tools/samples/v1/files/d4cb12ea8a768582562e1f1c0c930ea6fc4757f5b66551b986b41498efd75ca1/mobilenet-dog.jpg"
}
Rerun when
Artifact revision; Runtime version; Fixture or quality gate; Browser backend
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9826268331447399,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 1432.6000000238419,
      "loadMs": 4628.600000023842,
      "totalMs": 6061.200000047684,
      "grade": "usable",
      "imagesPerSecond": 0.6980315510144894,
      "version": "4.3.2",
      "artifactRevision": "a1308f1b8cdb1ec5ed5b32424d03b09e8d207a59",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8279603337848459,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 1474.300000011921,
      "loadMs": 4628.600000023842,
      "totalMs": 6102.900000035763,
      "grade": "usable",
      "imagesPerSecond": 0.6782880010797763,
      "version": "4.3.2",
      "artifactRevision": "a1308f1b8cdb1ec5ed5b32424d03b09e8d207a59",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 1452.1000000238419,
      "loadMs": 4628.600000023842,
      "totalMs": 6080.700000047684,
      "grade": "usable",
      "imagesPerSecond": 0.6886578059249233,
      "version": "4.3.2",
      "artifactRevision": "a1308f1b8cdb1ec5ed5b32424d03b09e8d207a59",
      "device": "wasm",
      "precision": "fp32",
      "gpuDispatches": 0
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.9826268331447399,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 115,
      "loadMs": 2820.300000011921,
      "totalMs": 2935.300000011921,
      "grade": "fast",
      "imagesPerSecond": 8.695652173913043,
      "version": "4.3.2",
      "artifactRevision": "a1308f1b8cdb1ec5ed5b32424d03b09e8d207a59",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 36
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0.8279603337848459,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 50.80000001192093,
      "loadMs": 2820.300000011921,
      "totalMs": 2871.100000023842,
      "grade": "fast",
      "imagesPerSecond": 19.68503936545937,
      "version": "4.3.2",
      "artifactRevision": "a1308f1b8cdb1ec5ed5b32424d03b09e8d207a59",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 36
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "maximumIoU": 0,
      "passed": true
    },
    "runtime": {
      "inferenceMs": 46.80000001192093,
      "loadMs": 2820.300000011921,
      "totalMs": 2867.100000023842,
      "grade": "fast",
      "imagesPerSecond": 21.367521362078616,
      "version": "4.3.2",
      "artifactRevision": "a1308f1b8cdb1ec5ed5b32424d03b09e8d207a59",
      "device": "webgpu",
      "precision": "fp32",
      "gpuDispatches": 36
    }
  }
]

Something not quite right?

Tell us what happened with RF-DETR. 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.