LFM3 Omni 2B Text
4 configurations testedQuality criteria
No explicit quality gate recorded. Review per-case evidence; full certification is pending.
| Precision | Device | Result | |
|---|---|---|---|
Q4F16 | GPU · WebGPUAccelerated | Passed | Fast |
Q4F16 | GPU · WebGPUAccelerated | Passed | Fast |
Q4F16 | CPU · WASM | Passed | Slow |
Q4F16 | CPU · WASM | Passed | Slow |
Test setup & sample details
- Quality gate
- No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
- Tested
- 2026-11-15T23:04:07.327Z
- Environment
- Chrome 157 on Apple M3 Max with persistent B2 mirror active.
- Runtime
- ONNX Runtime Web 1.31.0-dev.20260914-8d85527a0
- Artifact revision
- d2e656f0bddfaa2b8ebd4bfbe9d88de7897ee592
- Fixture
{ "file": "model-samples/lfm3-omni-2b/omni-native-samples/arithmetic-request.json", "url": "https://assets.localai.tools/samples/v1/files/ac9fb80d1c82c10cacb3dd396f0a2485b768eb67bfdefe030d3b9cb60fd8e809/arithmetic-request.json", "size": 252, "sha1": "edbe8f676bc4c4cb482e4c6dea5ae88b3d289c14", "sha256": "ac9fb80d1c82c10cacb3dd396f0a2485b768eb67bfdefe030d3b9cb60fd8e809" }- Rerun when
- artifact revision; runtime version; fixture checksum; quality gate; backend behavior
Per-case quality & failure details
[
{
"precision": "q4f16",
"device": "webgpu",
"status": "pass",
"quality": {
"metric": "exactAnswerMatch",
"score": 1,
"passed": true,
"expected": "15"
},
"runtime": {
"loadMs": 3300.875,
"inferenceMs": 474.9850000143051,
"totalMs": 3775.860000014305,
"precision": "q4f16",
"device": "webgpu",
"placement": "hybrid",
"engine": "ONNX Runtime Web",
"version": "1.31.0-dev.20260914-8d85527a0",
"artifactRevision": "d2e656f0bddfaa2b8ebd4bfbe9d88de7897ee592",
"performanceMetric": {
"name": "exactAnswerMatch",
"value": 1
},
"grade": "excellent"
}
},
{
"precision": "q4f16",
"device": "webgpu",
"status": "pass",
"quality": {
"metric": "exactAnswerMatch",
"score": 1,
"passed": true,
"expected": "quartz"
},
"runtime": {
"loadMs": 3300.875,
"inferenceMs": 256.5649999976158,
"totalMs": 3557.439999997616,
"precision": "q4f16",
"device": "webgpu",
"placement": "hybrid",
"engine": "ONNX Runtime Web",
"version": "1.31.0-dev.20260914-8d85527a0",
"artifactRevision": "d2e656f0bddfaa2b8ebd4bfbe9d88de7897ee592",
"performanceMetric": {
"name": "exactAnswerMatch",
"value": 1
},
"grade": "excellent"
}
},
{
"precision": "q4f16",
"device": "wasm",
"status": "pass",
"quality": {
"metric": "exactAnswerMatch",
"score": 1,
"passed": true,
"expected": "15"
},
"runtime": {
"loadMs": 3564.5800000429153,
"inferenceMs": 2025.2299999594688,
"totalMs": 5589.810000002384,
"precision": "q4f16",
"device": "wasm",
"placement": "cpu",
"engine": "ONNX Runtime Web",
"version": "1.31.0-dev.20260914-8d85527a0",
"artifactRevision": "d2e656f0bddfaa2b8ebd4bfbe9d88de7897ee592",
"performanceMetric": {
"name": "exactAnswerMatch",
"value": 1
},
"grade": "excellent"
}
},
{
"precision": "q4f16",
"device": "wasm",
"status": "pass",
"quality": {
"metric": "exactAnswerMatch",
"score": 1,
"passed": true,
"expected": "quartz"
},
"runtime": {
"loadMs": 3564.5800000429153,
"inferenceMs": 2317.6349999904633,
"totalMs": 5882.215000033379,
"precision": "q4f16",
"device": "wasm",
"placement": "cpu",
"engine": "ONNX Runtime Web",
"version": "1.31.0-dev.20260914-8d85527a0",
"artifactRevision": "d2e656f0bddfaa2b8ebd4bfbe9d88de7897ee592",
"performanceMetric": {
"name": "exactAnswerMatch",
"value": 1
},
"grade": "excellent"
}
}
]