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.

SmolVLM2 256M — Image + Text

Answer English text questions or questions about a still image locally with the compact SmolVLM2 256M model.

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

Answer English text questions or questions about a still image locally with the compact SmolVLM2 256M model.

Created by
Hugging Face
License
Apache-2.0
Model released
Feb 20, 2025
Source repository created
Feb 11, 2025
Model weights · Q4
264.2 MB

Best for

  • Simple image descriptions
  • Basic visual questions

Keep in mind

  • Experimental 256M checkpoint; can hallucinate objects, text and details.
  • Not suitable for safety-critical decisions or identification of people.
  • Poor lighting, small text and complex scenes reduce accuracy.
  • This adapter currently accepts one image; video decoding and temporal understanding are not advertised.
  • Browser quality evidence covers the supplied fixture only; this is not broad task validation.
  • Sampled video failed the fixed forward/reversed frame-order quality gate on both tested precisions. Video input is unavailable in this adapter.

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
HuggingFaceTB/SmolVLM2-256M-Video-Instruct
Release verification
Verified
Release evidence
Original announcement explicitly releases the 256M video checkpoint.
Source updated
Apr 8, 2025
Browser model files
HuggingFaceTB/SmolVLM2-256M-Video-Instruct
Files updated
Apr 8, 2025
Artifact revision
067788b187b95ebe7b2e040b3e4299e342e5b8fd

Input

IMAGE

Sample result

SmolVLM2 256M — Image + Text

Settings

Maximum generated answer tokens, from 1 to 256. Lower values can truncate captions or document text. Higher values allow longer output at greater time and memory cost.
Advanced settings 1
Include the input image and answer as a self-contained SVG. Turn off to return only answer text and avoid presentation processing.

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.

SmolVLM2 256M — Image + Text

28 configurations tested
Passed10
Failed18
TestedNov 4, 2026
RuntimeTransformers.js 4.2.0

Quality criteria

Nonempty, non-repetitive caption with at least five words and a person label matching the independently specified portrait reference.

PrecisionDeviceResult
Q4GPU · WebGPUAcceleratedPassedFast
FP32GPU · WebGPUAcceleratedPassedModerate
FP32GPU · WebGPUAcceleratedPassedModerate
Q4GPU · WebGPUAcceleratedPassedModerate
Q4GPU · WebGPUAcceleratedPassedModerate
FP32GPU · WebGPUAcceleratedPassedModerate
FP32GPU · WebGPUAcceleratedPassedSlow
FP32GPU · WebGPUAcceleratedPassedSlow
Q4GPU · WebGPUAcceleratedPassedSlow
Q4GPU · WebGPUAcceleratedPassedSlow
Q8CPU · WASMFailed—
Q8GPU · WebGPUFailed—
Q4CPU · WASMFailed—
FP32CPU · WASMFailed—
FP16CPU · WASMFailed—
FP16GPU · WebGPUFailed—
Q4F16CPU · WASMFailed—
Q4F16GPU · WebGPUFailed—
INT8CPU · WASMFailed—
INT8GPU · WebGPUFailed—
UINT8CPU · WASMFailed—
UINT8GPU · WebGPUFailed—
BNB4CPU · WASMFailed—
BNB4GPU · WebGPUFailed—
FP32GPU · WebGPUFailed—
FP32GPU · WebGPUFailed—
Q4GPU · WebGPUFailed—
Q4GPU · WebGPUFailed—
Test setup & sample details
Quality gate
Nonempty, non-repetitive caption with at least five words and a person label matching the independently specified portrait reference.
Tested
2026-11-04T17:45:47.085Z
Environment
Isolated Chrome 156.0.8078.79 module worker per case on macOS arm64; Transformers.js 4.2.0; cold model cache
Runtime
Transformers.js 4.2.0
Artifact revision
067788b187b95ebe7b2e040b3e4299e342e5b8fd
Fixture
{
  "file": "model-samples/lfm2-vl-450m.json",
  "url": "https://f005.backblazeb2.com/file/hubters-webai-public/assets/benchmarks/lfm2-vl-450m.json",
  "size": 417,
  "sha1": "2c1a441093498eea1887511f171471d1bfc608a3"
}
Rerun when
artifact revision change; runtime version change; fixture or quality-gate change; browser/backend behavior change
Per-case quality & failure details
[
  {
    "precision": "q8",
    "device": "wasm",
    "status": "fail",
    "quality": {
      "personMention": true,
      "wordCount": 54,
      "uniqueRatio": 0.7407407407407407,
      "passed": true,
      "visualization": true
    },
    "runtime": {
      "loadMs": 1877.9000000059605,
      "inferenceMs": 77445.59999999404,
      "totalMs": 80712.59999999404,
      "grade": "very-slow",
      "imagesPerSecond": 0.012912289400560871,
      "artifactRevision": "067788b187b95ebe7b2e040b3e4299e342e5b8fd",
      "engine": {
        "name": "Transformers.js",
        "version": "4.2.0"
      }
    },
    "failure": "Quality or 15-second interactive usability gate failed"
  },
  {
    "precision": "q8",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "personMention": true,
      "wordCount": 6,
      "uniqueRatio": 1,
      "passed": true,
      "visualization": true
    },
    "runtime": {
      "loadMs": 1975.4000000059605,
      "inferenceMs": 64148.19999998808,
      "totalMs": 67664.89999997616,
      "grade": "very-slow",
      "imagesPerSecond": 0.015588901948927418,
      "artifactRevision": "067788b187b95ebe7b2e040b3e4299e342e5b8fd",
      "engine": {
        "name": "Transformers.js",
        "version": "4.2.0"
      }
    },
    "failure": "Quality or 15-second interactive usability gate failed"
  },
  {
    "precision": "q4",
    "device": "wasm",
    "status": "fail",
    "quality": {
      "personMention": true,
      "wordCount": 12,
      "uniqueRatio": 0.8333333333333334,
      "passed": true,
      "visualization": true
    },
    "runtime": {
      "loadMs": 6261.9000000059605,
      "inferenceMs": 79937.5,
      "totalMs": 88018.69999998808,
      "grade": "very-slow",
      "imagesPerSecond": 0.012509773260359656,
      "artifactRevision": "067788b187b95ebe7b2e040b3e4299e342e5b8fd",
      "engine": {
        "name": "Transformers.js",
        "version": "4.2.0"
      }
    },
    "failure": "Quality or 15-second interactive usability gate failed"
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "personMention": true,
      "wordCount": 12,
      "uniqueRatio": 0.8333333333333334,
      "passed": true,
      "visualization": true
    },
    "runtime": {
      "loadMs": 2221.0999999940395,
      "inferenceMs": 3561.800000011921,
      "totalMs": 7279.800000011921,
      "grade": "good",
      "imagesPerSecond": 0.2807569206571546,
      "artifactRevision": "067788b187b95ebe7b2e040b3e4299e342e5b8fd",
      "engine": {
        "name": "Transformers.js",
        "version": "4.2.0"
      }
    }
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 2378.800000011921,
      "inferenceMs": null,
      "totalMs": 51758.79999998212,
      "grade": "failed"
    },
    "failure": "generate timeout"
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "personMention": true,
      "wordCount": 16,
      "uniqueRatio": 0.8125,
      "passed": true,
      "visualization": true
    },
    "runtime": {
      "loadMs": 2400.199999988079,
      "inferenceMs": 2918.800000011921,
      "totalMs": 6831.5,
      "grade": "good",
      "imagesPerSecond": 0.34260655063584894,
      "artifactRevision": "067788b187b95ebe7b2e040b3e4299e342e5b8fd",
      "engine": {
        "name": "Transformers.js",
        "version": "4.2.0"
      }
    }
  },
  {
    "precision": "fp16",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": null,
      "inferenceMs": null,
      "totalMs": 3233.9000000059605,
      "grade": "failed"
    },
    "failure": "Can't create a session. ERROR_CODE: 1, ERROR_MESSAGE: /mnt/vss/_work/1/s/onnxruntime/core/graph/graph_utils.cc:30 int onnxruntime::graph_utils::GetIndexFromName(const Node &, const std::string &, bool) itr != node_args.end() was false. Attempting to get index by a name which does not exist:InsertedPrecisionFreeCast_/vision_model/encoder/layers.0/layer_norm1/Constant_output_0for node: /vision_model/encoder/layers.0/layer_norm1/Mul/SimplifiedLayerNormFusion/\n"
  },
  {
    "precision": "fp16",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "personMention": false,
      "wordCount": 1,
      "uniqueRatio": 1,
      "passed": false,
      "visualization": true
    },
    "runtime": {
      "loadMs": 2274.2999999821186,
      "inferenceMs": 3691.9000000059605,
      "totalMs": 7308.199999988079,
      "grade": "good",
      "imagesPerSecond": 0.2708632411491063,
      "artifactRevision": "067788b187b95ebe7b2e040b3e4299e342e5b8fd",
      "engine": {
        "name": "Transformers.js",
        "version": "4.2.0"
      }
    },
    "failure": "Quality or 15-second interactive usability gate failed"
  },
  {
    "precision": "q4f16",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": null,
      "inferenceMs": null,
      "totalMs": 3380.300000011921,
      "grade": "failed"
    },
    "failure": "Can't create a session. ERROR_CODE: 1, ERROR_MESSAGE: /mnt/vss/_work/1/s/onnxruntime/core/graph/graph_utils.cc:30 int onnxruntime::graph_utils::GetIndexFromName(const Node &, const std::string &, bool) itr != node_args.end() was false. Attempting to get index by a name which does not exist:InsertedPrecisionFreeCast_/vision_model/encoder/layers.0/layer_norm1/Constant_output_0for node: /vision_model/encoder/layers.0/layer_norm1/Mul/SimplifiedLayerNormFusion/\n"
  },
  {
    "precision": "q4f16",
    "device": "webgpu",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 2172.2999999821186,
      "inferenceMs": null,
      "totalMs": 5247.5999999940395,
      "grade": "failed"
    },
    "failure": "Model returned empty answer"
  },
  {
    "precision": "int8",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 1975.199999988079,
      "inferenceMs": null,
      "totalMs": 51337.90000000596,
      "grade": "failed"
    },
    "failure": "generate timeout"
  },
  {
    "precision": "int8",
    "device": "webgpu",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 2039.5999999940395,
      "inferenceMs": null,
      "totalMs": 48817.69999998808,
      "grade": "failed"
    },
    "failure": "generate timeout"
  },
  {
    "precision": "uint8",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 1870.5,
      "inferenceMs": null,
      "totalMs": 51209,
      "grade": "failed"
    },
    "failure": "generate timeout"
  },
  {
    "precision": "uint8",
    "device": "webgpu",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 2088.5,
      "inferenceMs": null,
      "totalMs": 49201.70000001788,
      "grade": "failed"
    },
    "failure": "generate timeout"
  },
  {
    "precision": "bnb4",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 2230.7999999821186,
      "inferenceMs": null,
      "totalMs": 51683.19999998808,
      "grade": "failed"
    },
    "failure": "generate timeout"
  },
  {
    "precision": "bnb4",
    "device": "webgpu",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 2031.2999999821186,
      "inferenceMs": null,
      "totalMs": 49187.19999998808,
      "grade": "failed"
    },
    "failure": "generate timeout"
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 42457.889999985695,
      "inferenceMs": 3401.4700000286102,
      "totalMs": 45859.564999997616,
      "wallMs": 3401.675000011921,
      "charactersPerSecond": 1.7639432362918188,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.29399053938196984
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 42457.889999985695,
      "inferenceMs": 1709.8950000405312,
      "totalMs": 47569.54500001669,
      "wallMs": 1709.9700000286102,
      "charactersPerSecond": 8.187637252385759,
      "inputModality": "image",
      "grade": "good",
      "imagesPerSecond": 0.5848312323132684
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 42457.889999985695,
      "inferenceMs": 1549.5799999833107,
      "totalMs": 49119.18000000715,
      "wallMs": 1549.625,
      "charactersPerSecond": 1.2906723112208085,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.6453361556104042
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "failed",
      "score": 0,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 42457.889999985695,
      "inferenceMs": 1245.7699999809265,
      "totalMs": 50365,
      "wallMs": 1245.8100000023842,
      "charactersPerSecond": 4.013581961418684,
      "inputModality": "video",
      "grade": "slow",
      "framesPerSecond": 3.2108655691349464
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "failed",
      "score": 0,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 42457.889999985695,
      "inferenceMs": 1147.8550000190735,
      "totalMs": 51512.87000000477,
      "wallMs": 1147.8650000095367,
      "charactersPerSecond": 4.35595088222547,
      "inputModality": "video",
      "grade": "slow",
      "framesPerSecond": 3.484760705780376
    }
  },
  {
    "precision": "fp32",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 42457.889999985695,
      "inferenceMs": 1257.5649999976158,
      "totalMs": 52770.485000014305,
      "wallMs": 1257.6150000095367,
      "charactersPerSecond": 205.1583814757004,
      "inputModality": "text",
      "grade": "fast"
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 43917.89500004053,
      "inferenceMs": 3472.9900000095367,
      "totalMs": 47391.11500000954,
      "wallMs": 3473.2199999690056,
      "charactersPerSecond": 5.75872663035168,
      "inputModality": "image",
      "grade": "good",
      "imagesPerSecond": 0.28793633151758397
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 43917.89500004053,
      "inferenceMs": 1658.010000050068,
      "totalMs": 49049.205000042915,
      "wallMs": 1658.085000038147,
      "charactersPerSecond": 8.443857395056263,
      "inputModality": "image",
      "grade": "good",
      "imagesPerSecond": 0.6031326710754473
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 43917.89500004053,
      "inferenceMs": 1580.0400000214577,
      "totalMs": 50629.30500000715,
      "wallMs": 1580.089999973774,
      "charactersPerSecond": 1.26579073945776,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.6328953697288799
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "failed",
      "score": 0,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 43917.89500004053,
      "inferenceMs": 1333.9400000572205,
      "totalMs": 51963.29500001669,
      "wallMs": 1333.9900000095367,
      "charactersPerSecond": 2.9986356206639107,
      "inputModality": "video",
      "grade": "slow",
      "framesPerSecond": 2.9986356206639107
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "failed",
      "score": 0,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 43917.89500004053,
      "inferenceMs": 1175.7699999809265,
      "totalMs": 53139.080000042915,
      "wallMs": 1175.785000026226,
      "charactersPerSecond": 3.402025906482465,
      "inputModality": "video",
      "grade": "slow",
      "framesPerSecond": 3.4020259064824656
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 43917.89500004053,
      "inferenceMs": 104.23500001430511,
      "totalMs": 53243.37999999523,
      "wallMs": 104.29999995231628,
      "charactersPerSecond": 306.99860887042115,
      "inputModality": "text",
      "grade": "fast"
    }
  }
]

SmolVLM2 500M — Text, Image

10 configurations tested
Passed7
Failed3
TestedNov 4, 2026
RuntimeTransformers.js 4.2.0

Quality criteria

Nonempty, non-repetitive caption with at least five words and a person label matching the independently specified portrait reference.

PrecisionDeviceResult
Q4GPU · WebGPUAcceleratedPassedFast
Q4GPU · WebGPUAcceleratedPassedModerate
Q4GPU · WebGPUAcceleratedPassedModerate
Q4GPU · WebGPUAcceleratedPassedModerate
Q4GPU · WebGPUAcceleratedPassedModerate
Q4GPU · WebGPUAcceleratedPassedSlow
Q4GPU · WebGPUAcceleratedPassedSlow
Q4CPU · WASMFailed—
Q4F16CPU · WASMFailed—
Q4F16GPU · WebGPUFailed—
Test setup & sample details
Quality gate
Nonempty, non-repetitive caption with at least five words and a person label matching the independently specified portrait reference.
Tested
2026-11-04T22:30:13.966Z
Environment
Isolated Chrome 156.0.8078.79 module worker per case on macOS arm64; Transformers.js 4.2.0; cold model cache
Runtime
Transformers.js 4.2.0
Artifact revision
7b375e1b73b11138ff12fe22c8f2822d8fe03467
Fixture
{
  "file": "model-samples/lfm2-vl-450m.json",
  "url": "https://f005.backblazeb2.com/file/hubters-webai-public/assets/benchmarks/lfm2-vl-450m.json",
  "size": 417,
  "sha1": "2c1a441093498eea1887511f171471d1bfc608a3"
}
Rerun when
artifact revision change; runtime version change; fixture or quality-gate change; browser/backend behavior change
Per-case quality & failure details
[
  {
    "precision": "q4",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": 1867.9000000357628,
      "inferenceMs": null,
      "totalMs": 51198.700000047684,
      "grade": "failed"
    },
    "failure": "generate timeout"
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "personMention": true,
      "wordCount": 48,
      "uniqueRatio": 0.625,
      "passed": true,
      "visualization": true
    },
    "runtime": {
      "loadMs": 2128.699999988079,
      "inferenceMs": 4448.200000047684,
      "totalMs": 16178,
      "grade": "good",
      "imagesPerSecond": 0.2248100355175757,
      "artifactRevision": "7b375e1b73b11138ff12fe22c8f2822d8fe03467",
      "engine": {
        "name": "Transformers.js",
        "version": "4.2.0"
      }
    }
  },
  {
    "precision": "q4f16",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": null,
      "inferenceMs": null,
      "totalMs": 3366.300000011921,
      "grade": "failed"
    },
    "failure": "Can't create a session. ERROR_CODE: 1, ERROR_MESSAGE: /mnt/vss/_work/1/s/onnxruntime/core/graph/graph_utils.cc:30 int onnxruntime::graph_utils::GetIndexFromName(const Node &, const std::string &, bool) itr != node_args.end() was false. Attempting to get index by a name which does not exist:InsertedPrecisionFreeCast_/vision_model/encoder/layers.0/layer_norm1/Constant_output_0for node: /vision_model/encoder/layers.0/layer_norm1/Mul/SimplifiedLayerNormFusion/\n"
  },
  {
    "precision": "q4f16",
    "device": "webgpu",
    "status": "fail",
    "quality": {
      "personMention": true,
      "wordCount": 24,
      "uniqueRatio": 0.5416666666666666,
      "passed": false,
      "visualization": true
    },
    "runtime": {
      "loadMs": 2144,
      "inferenceMs": 3313.599999964237,
      "totalMs": 12195.699999988079,
      "grade": "good",
      "imagesPerSecond": 0.3017865765363329,
      "artifactRevision": "7b375e1b73b11138ff12fe22c8f2822d8fe03467",
      "engine": {
        "name": "Transformers.js",
        "version": "4.2.0"
      }
    },
    "failure": "Quality or 15-second interactive usability gate failed"
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 23551.959999978542,
      "inferenceMs": 4339.535000026226,
      "totalMs": 27891.694999992847,
      "wallMs": 4339.735000014305,
      "charactersPerSecond": 1.1521971824100468,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.23043943648200935
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 23551.959999978542,
      "inferenceMs": 1907.7900000214577,
      "totalMs": 29799.564999997616,
      "wallMs": 1907.8650000095367,
      "charactersPerSecond": 7.338333883625838,
      "inputModality": "image",
      "grade": "good",
      "imagesPerSecond": 0.5241667059732741
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 23551.959999978542,
      "inferenceMs": 1828.5799999833107,
      "totalMs": 31628.214999973774,
      "wallMs": 1828.6399999856949,
      "charactersPerSecond": 1.0937448730808899,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.546872436540445
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 23551.959999978542,
      "inferenceMs": 1321.2700000405312,
      "totalMs": 32949.52999997139,
      "wallMs": 1321.3100000023842,
      "charactersPerSecond": 7.568475784429557,
      "inputModality": "video",
      "grade": "good",
      "framesPerSecond": 3.0273903137718228
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 23551.959999978542,
      "inferenceMs": 1300.7350000143051,
      "totalMs": 34250.28999996185,
      "wallMs": 1300.75,
      "charactersPerSecond": 7.687961037328912,
      "inputModality": "video",
      "grade": "good",
      "framesPerSecond": 3.075184414931565
    }
  },
  {
    "precision": "q4",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "nonEmpty": true,
      "gibberish": false,
      "grade": "fixture-pass",
      "score": 1,
      "scope": "Fixed English object/OCR/count, color-order or capital-city fixture; not broad model quality certification."
    },
    "runtime": {
      "loadMs": 23551.959999978542,
      "inferenceMs": 114.72499996423721,
      "totalMs": 34365.07499998808,
      "wallMs": 114.78500002622604,
      "charactersPerSecond": 278.9278710828088,
      "inputModality": "text",
      "grade": "fast"
    }
  }
]
Unavailable checkpoints (2)

These checkpoints have not passed the required browser checks.

2.2B · Instruct · Official checkpoint; requires its own browser artifacts, WebGPU/WASM quality, memory, streaming and complete sample-output validation.

2.2B · Base · Official checkpoint; browser artifacts, WebGPU/WASM quality, memory, streaming and complete sample output are unverified. Base weights also require a suitable task interface.

Something not quite right?

Tell us what happened with SmolVLM2. 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.