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.

Qwen3.5 0.8B — Text, Image

Chat locally with text and still images using the complete Qwen3.5 checkpoint.

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

Chat locally with text and still images using the complete Qwen3.5 checkpoint.

License
Apache-2.0
Model released
Mar 2, 2026
Source repository created
Feb 28, 2026
Model weights · Q4F16
646.8 MB

Best for

  • Local chat, drafting, rewriting, and summarization.
  • Benchmarking browser LLM inference.

Keep in mind

  • Generated text may be incorrect, unsafe, or fabricated and requires review.
  • The model is small and trades reasoning quality for browser memory and speed.
  • Video and sampled video-frame inputs are not supported. Use a still image instead.

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
Qwen/Qwen3.5-0.8B
Release verification
Verified
Release evidence
Official news releases 0.8B/2B/4B/9B sizes on March 2; initial larger checkpoint release does not apply.
Source updated
Mar 2, 2026
Browser model files
onnx-community/Qwen3.5-0.8B-ONNX
Files updated
Oct 13, 2026
Artifact revision
8fe9dbe3fb39fe902e18df9be84b6a0ac77ae0f6

Input

CHAT & TEXT

Sample result

Qwen3.5 0.8B — Text, Image

Settings

Limits the number of newly generated output tokens. Lower values finish sooner but can cut answers short. Higher values allow longer answers and can use more time and memory; they do not guarantee better answers.
Advanced settings 6
Adjusts randomness during token sampling. Lower values favor likely tokens and more repeatable wording. Higher values increase variation and can increase mistakes. It affects sampling only; some runtimes use zero for greedy decoding.
Chooses sampled rather than greedy token selection. On allows varied responses and makes sampling controls relevant. Off favors the most likely tokens for more repeatable responses; it does not guarantee correctness.
Sampling candidate count; used only when sampling is enabled. Lower values narrow sampling choices. Higher values increase variety without guaranteeing accuracy.
Cumulative probability threshold for sampling; direct API requires0<top_p<=1. Lower values narrow sampled choices; higher values allow more variety. Used only with sampling.
Positive repetition penalty;1leaves token scores unchanged. Values above1discourage repetition, while values below1encourage it. Strong penalties can harm coherent output.
Include the input image and answer as a self-contained SVG. Turn off to return only answer text and avoid presentation processing.
Estimated speedNot benchmarked

Output

Start a conversation

Send a message or try a sample. Replies appear here.

Benchmark evidence

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

Qwen3.5 0.8B — Text, Image

35 configurations tested
Passed24
Failed11
TestedNov 5, 2026
RuntimeTransformers.js 4.2.0

Quality criteria

{ "version": "multimodal-v1", "scope": "Fixed English object, printed-text, counting, ordered-frame and capital-city checks. Modality support is scoped to each precision/device.", "references": "research/multimodal-llm-audit/fixtures.json", "nonEmpty": true, "nonRepetitive": true }

PrecisionDeviceResult
Q8GPU · WebGPUAcceleratedPassedModerate
FP16GPU · WebGPUAcceleratedPassedModerate
Q4F16GPU · WebGPUAcceleratedPassedModerate
FP32GPU · WebGPUAcceleratedPassedModerate
Q4GPU · WebGPUAcceleratedPassedModerate
FP16GPU · WebGPUAcceleratedPassedVery slow
FP16GPU · WebGPUAcceleratedPassedVery slow
FP32GPU · WebGPUAcceleratedPassedVery slow
Q8GPU · WebGPUAcceleratedPassedVery slow
FP16GPU · WebGPUAcceleratedPassedVery slow
Q4F16GPU · WebGPUAcceleratedPassedVery slow
Q4F16GPU · WebGPUAcceleratedPassedVery slow
FP16GPU · WebGPUAcceleratedPassedVery slow
Q8GPU · WebGPUAcceleratedPassedVery slow
FP32GPU · WebGPUAcceleratedPassedVery slow
Q8GPU · WebGPUAcceleratedPassedVery slow
Q4GPU · WebGPUAcceleratedPassedVery slow
Q4GPU · WebGPUAcceleratedPassedVery slow
Q4F16GPU · WebGPUAcceleratedPassedVery slow
Q4GPU · WebGPUAcceleratedPassedVery slow
FP32GPU · WebGPUAcceleratedPassedVery slow
FP16GPU · WebGPUAcceleratedPassedVery slow
Q8GPU · WebGPUAcceleratedPassedVery slow
FP32GPU · WebGPUAcceleratedPassedVery slow
FP16CPU · WASMFailed—
FP32CPU · WASMFailed—
Q4CPU · WASMFailed—
Q4F16CPU · WASMFailed—
Q8CPU · WASMFailed—
FP32GPU · WebGPUFailed—
Q4GPU · WebGPUFailed—
Q4GPU · WebGPUFailed—
Q4F16GPU · WebGPUFailed—
Q4F16GPU · WebGPUFailed—
Q8GPU · WebGPUFailed—
Test setup & sample details
Quality gate
{ "version": "multimodal-v1", "scope": "Fixed English object, printed-text, counting, ordered-frame and capital-city checks. Modality support is scoped to each precision/device.", "references": "research/multimodal-llm-audit/fixtures.json", "nonEmpty": true, "nonRepetitive": true }
Tested
2026-11-05T15:03:40.192Z
Environment
Not recorded
Runtime
Transformers.js 4.2.0
Artifact revision
8fe9dbe3fb39fe902e18df9be84b6a0ac77ae0f6
Fixture
{
  "file": "model-samples/multimodal/qwen3.5-0.8b-text-regression-fixture.json",
  "url": "https://assets.localai.tools/samples/v1/files/a1fb53a41e7676c395e3feb366f30d88db75fca4bd55c85c88c023d5a3a0d6bb/qwen3.5-0.8b-text-regression-fixture.json",
  "size": 424,
  "sha1": "b1328ae38cb093ad33065cfa8034413e69cf28e0",
  "sha256": "a1fb53a41e7676c395e3feb366f30d88db75fca4bd55c85c88c023d5a3a0d6bb"
}
Rerun when
artifact revision change; runtime version change; fixture or quality gate change; browser/backend change; Input modality preprocessing or modality-specific quality gates
Per-case quality & failure details
[
  {
    "precision": "fp16",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": null,
      "inferenceMs": null,
      "totalMs": null,
      "grade": "failed"
    },
    "failure": "Error: [WorkerError:runtime_error] init: Error: Can't create a session. ERROR_CODE: 6, ERROR_MESSAGE: std::bad_alloc\n    at Le (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:12:31247)\n    at Id (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:22953)\n    at async $2.loadModel (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:35835)\n    at async gd.createInferenceSessionHandler (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:37556)\n    at async u2.create (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:10:47888)\n    at async Pc (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:54332)\n    at async https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16886\n    at async Promise.all (index 1)\n    at async RT (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16743)\n    at async Promise.all (index 0)"
  },
  {
    "precision": "fp32",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": null,
      "inferenceMs": null,
      "totalMs": null,
      "grade": "failed"
    },
    "failure": "Error: [WorkerError:runtime_error] init: Error: Can't create a session. ERROR_CODE: 6, ERROR_MESSAGE: std::bad_alloc\n    at Le (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:12:31247)\n    at Id (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:22953)\n    at async $2.loadModel (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:35835)\n    at async gd.createInferenceSessionHandler (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:37556)\n    at async u2.create (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:10:47888)\n    at async Pc (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:54332)\n    at async https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16886\n    at async Promise.all (index 1)\n    at async RT (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16743)\n    at async Promise.all (index 0)"
  },
  {
    "precision": "q4",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": null,
      "inferenceMs": null,
      "totalMs": null,
      "grade": "failed"
    },
    "failure": "Error: [WorkerError:runtime_error] init: Error: Can't create a session. ERROR_CODE: 9, ERROR_MESSAGE: Could not find an implementation for GatherBlockQuantized(1) node with name '/model/pos_embed/emb_00_Quant'\n    at Le (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:12:31247)\n    at Id (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:22953)\n    at async $2.loadModel (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:35835)\n    at async gd.createInferenceSessionHandler (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:37556)\n    at async u2.create (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:10:47888)\n    at async Pc (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:54332)\n    at async https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16886\n    at async Promise.all (index 2)\n    at async RT (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16743)\n    at async Promise.all (index 0)"
  },
  {
    "precision": "q4f16",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": null,
      "inferenceMs": null,
      "totalMs": null,
      "grade": "failed"
    },
    "failure": "Error: [WorkerError:runtime_error] init: Error: Can't create a session. ERROR_CODE: 9, ERROR_MESSAGE: Could not find an implementation for GatherBlockQuantized(1) node with name '/model/pos_embed/emb_00_Quant'\n    at Le (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:12:31247)\n    at Id (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:22953)\n    at async $2.loadModel (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:35835)\n    at async gd.createInferenceSessionHandler (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:37556)\n    at async u2.create (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:10:47888)\n    at async Pc (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:54332)\n    at async https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16886\n    at async Promise.all (index 2)\n    at async RT (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16743)\n    at async Promise.all (index 0)"
  },
  {
    "precision": "q8",
    "device": "wasm",
    "status": "fail",
    "quality": "Not embedded",
    "runtime": {
      "loadMs": null,
      "inferenceMs": null,
      "totalMs": null,
      "grade": "failed"
    },
    "failure": "Error: [WorkerError:runtime_error] init: Error: Can't create a session. ERROR_CODE: 9, ERROR_MESSAGE: Could not find an implementation for GatherBlockQuantized(1) node with name '/model/pos_embed/emb_00_Quant'\n    at Le (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:12:31247)\n    at Id (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:22953)\n    at async $2.loadModel (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:35835)\n    at async gd.createInferenceSessionHandler (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:37556)\n    at async u2.create (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:10:47888)\n    at async Pc (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:13:54332)\n    at async https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16886\n    at async Promise.all (index 2)\n    at async RT (https://cdn.jsdelivr.net/npm/@huggingface/transformers@4.2.0:37:16743)\n    at async Promise.all (index 0)"
  },
  {
    "precision": "fp16",
    "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": 87471.94999998808,
      "inferenceMs": 29256.37999999523,
      "totalMs": 116728.53500002623,
      "wallMs": 29256.585000038147,
      "charactersPerSecond": 0.1367223149275697,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.034180578731892425
    }
  },
  {
    "precision": "fp16",
    "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": 87471.94999998808,
      "inferenceMs": 26417.769999980927,
      "totalMs": 143146.39499998093,
      "wallMs": 26417.849999964237,
      "charactersPerSecond": 0.4920930116360838,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.03785330858739106
    }
  },
  {
    "precision": "fp16",
    "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": 87471.94999998808,
      "inferenceMs": 24532.42500001192,
      "totalMs": 167678.88499999046,
      "wallMs": 24532.474999964237,
      "charactersPerSecond": 1.7120199083449594,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.04076237877011808
    }
  },
  {
    "precision": "fp16",
    "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": 87471.94999998808,
      "inferenceMs": 10604.660000026226,
      "totalMs": 178283.60000002384,
      "wallMs": 10604.710000038147,
      "charactersPerSecond": 0.7543853362559683,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.3771926681279841
    }
  },
  {
    "precision": "fp16",
    "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": 87471.94999998808,
      "inferenceMs": 11329.125,
      "totalMs": 189612.74000000954,
      "wallMs": 11329.139999985695,
      "charactersPerSecond": 0.7944126311608355,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.3530722805159269
    }
  },
  {
    "precision": "fp16",
    "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": 87471.94999998808,
      "inferenceMs": 763.4300000071526,
      "totalMs": 190376.24500000477,
      "wallMs": 763.5049999952316,
      "charactersPerSecond": 6.549388941950349,
      "inputModality": "text",
      "grade": "good"
    }
  },
  {
    "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": 167816.94499999285,
      "inferenceMs": 30783.55000001192,
      "totalMs": 198600.75499999523,
      "wallMs": 30783.805000007153,
      "charactersPerSecond": 0.1299395293914591,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.03248488234786478
    }
  },
  {
    "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": 167816.94499999285,
      "inferenceMs": 26696.064999997616,
      "totalMs": 225296.91000002623,
      "wallMs": 26696.150000035763,
      "charactersPerSecond": 0.48696315355844244,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.03745870411988019
    }
  },
  {
    "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": 167816.94499999285,
      "inferenceMs": 28828.725000023842,
      "totalMs": 254125.69499999285,
      "wallMs": 28828.774999976158,
      "charactersPerSecond": 1.4568802470440598,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.03468762492962047
    }
  },
  {
    "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": 167816.94499999285,
      "inferenceMs": 11565.399999976158,
      "totalMs": 265691.14500004053,
      "wallMs": 11565.445000052452,
      "charactersPerSecond": 0.6917184014402002,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.3458592007201001
    }
  },
  {
    "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": 167816.94499999285,
      "inferenceMs": 11957.264999985695,
      "totalMs": 277648.4250000119,
      "wallMs": 11957.274999976158,
      "charactersPerSecond": 0.8363116481914521,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.3345246592765808
    }
  },
  {
    "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": 167816.94499999285,
      "inferenceMs": 861.2700000405312,
      "totalMs": 278509.77000004053,
      "wallMs": 861.3400000333786,
      "charactersPerSecond": 5.805380426306154,
      "inputModality": "text",
      "grade": "good"
    }
  },
  {
    "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": 31029.585000038147,
      "inferenceMs": 28692.430000007153,
      "totalMs": 59722.21500003338,
      "wallMs": 28692.625,
      "charactersPerSecond": 0.20911439010214555,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.03485239835035759
    }
  },
  {
    "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": 31029.585000038147,
      "inferenceMs": 27612.464999973774,
      "totalMs": 87334.79000002146,
      "wallMs": 27612.569999992847,
      "charactersPerSecond": 0.47080186430339876,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.03621552802333836
    }
  },
  {
    "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": 31029.585000038147,
      "inferenceMs": 28245.37000000477,
      "totalMs": 115580.22500002384,
      "wallMs": 28245.42500001192,
      "charactersPerSecond": 1.3453532384243359,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.035404032590114105
    }
  },
  {
    "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": 31029.585000038147,
      "inferenceMs": 11748.785000026226,
      "totalMs": 127329.06000000238,
      "wallMs": 11748.82999998331,
      "charactersPerSecond": 0.9362670267585496,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.3404607370031089
    }
  },
  {
    "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": 31029.585000038147,
      "inferenceMs": 13568.830000042915,
      "totalMs": 140897.905000031,
      "wallMs": 13568.84500002861,
      "charactersPerSecond": 0.8106815399680893,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.29479328726112336
    }
  },
  {
    "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": 31029.585000038147,
      "inferenceMs": 902.3249999880791,
      "totalMs": 141800.31499999762,
      "wallMs": 902.4099999666214,
      "charactersPerSecond": 5.541240683862308,
      "inputModality": "text",
      "grade": "good"
    }
  },
  {
    "precision": "q4f16",
    "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": 28071.735000014305,
      "inferenceMs": 28396.799999952316,
      "totalMs": 56468.75,
      "wallMs": 28397.014999985695,
      "charactersPerSecond": 0.21129141311732572,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.035215235519554286
    }
  },
  {
    "precision": "q4f16",
    "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": 28071.735000014305,
      "inferenceMs": 25716.375,
      "totalMs": 82185.20500004292,
      "wallMs": 25716.455000042915,
      "charactersPerSecond": 0.5055144825038521,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.03888572942337324
    }
  },
  {
    "precision": "q4f16",
    "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": 28071.735000014305,
      "inferenceMs": 25627.680000007153,
      "totalMs": 107812.95000004768,
      "wallMs": 25627.740000009537,
      "charactersPerSecond": 1.4827717530416094,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.03902030929056867
    }
  },
  {
    "precision": "q4f16",
    "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": 28071.735000014305,
      "inferenceMs": 11670.004999995232,
      "totalMs": 119483.00499999523,
      "wallMs": 11670.049999952316,
      "charactersPerSecond": 0.9425874281977167,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.3427590647991697
    }
  },
  {
    "precision": "q4f16",
    "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": 28071.735000014305,
      "inferenceMs": 12865.444999992847,
      "totalMs": 132348.46000003815,
      "wallMs": 12865.449999988079,
      "charactersPerSecond": 0.855003460821302,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.31091034938956436
    }
  },
  {
    "precision": "q4f16",
    "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": 28071.735000014305,
      "inferenceMs": 832.1899999976158,
      "totalMs": 133180.74000000954,
      "wallMs": 832.2749999761581,
      "charactersPerSecond": 6.008243309838288,
      "inputModality": "text",
      "grade": "good"
    }
  },
  {
    "precision": "q8",
    "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": 51517.049999952316,
      "inferenceMs": 29423.225000023842,
      "totalMs": 80940.49000000954,
      "wallMs": 29423.445000052452,
      "charactersPerSecond": 0.13594702824033594,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.033986757060083986
    }
  },
  {
    "precision": "q8",
    "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": 51517.049999952316,
      "inferenceMs": 27504.399999976158,
      "totalMs": 108444.97499996424,
      "wallMs": 27504.474999964237,
      "charactersPerSecond": 0.47265164846392826,
      "inputModality": "image",
      "grade": "very-slow",
      "imagesPerSecond": 0.036357819112609865
    }
  },
  {
    "precision": "q8",
    "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": 51517.049999952316,
      "inferenceMs": 26608.035000026226,
      "totalMs": 135053.07499998808,
      "wallMs": 26608.100000023842,
      "charactersPerSecond": 1.4281400336388066,
      "inputModality": "image",
      "grade": "slow",
      "imagesPerSecond": 0.03758263246417912
    }
  },
  {
    "precision": "q8",
    "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": 51517.049999952316,
      "inferenceMs": 13060.870000004768,
      "totalMs": 148114.0299999714,
      "wallMs": 13060.939999997616,
      "charactersPerSecond": 0.6125166240837768,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.30625831204188847
    }
  },
  {
    "precision": "q8",
    "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": 51517.049999952316,
      "inferenceMs": 13550.0150000453,
      "totalMs": 161664.06000000238,
      "wallMs": 13550.030000030994,
      "charactersPerSecond": 0.885607875707878,
      "inputModality": "video",
      "grade": "very-slow",
      "framesPerSecond": 0.2952026252359593
    }
  },
  {
    "precision": "q8",
    "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": 51517.049999952316,
      "inferenceMs": 688.1349999904633,
      "totalMs": 162352.25999999046,
      "wallMs": 688.1949999928474,
      "charactersPerSecond": 7.266016116124444,
      "inputModality": "text",
      "grade": "good"
    }
  }
]

Something not quite right?

Tell us what happened with Qwen3.5. 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.