Laya Desktop
Classify text, assign ordered scores, and answer yes/no questions using the original multilingual Laya checkpoint.
Desktop app
Run Laya Desktop on your computer
Download the desktop app to load this model, provide input and view results locally.
Public desktop downloads are coming soon.Device requirements
If your device falls short
MemoryAdvisory only: close other apps, reduce image/tile/token/batch settings or choose a smaller verified model/precision. CPU can need more RAM than GPU.
GPUIf the selected GPU runtime fails, existing CPU fallback may recover when enabled, but CPU has its own memory/runtime needs.
PlatformUse a compatible OS/architecture/runtime or another model. These estimates do not add hardware detection or block runs.
Benchmark evidence
Saved desktop measurements apply to the recorded hardware and runtime. Fallback cases report the device that actually ran; they do not prove GPU support on the requested device.
Laya Multilingual Desktop
2 configurations testedQuality criteria
Every English, Chinese, and Spanish case must return finite normalized non-degenerate distributions and the checked-in expected choice/yes-no result or ordered-score interval.
| Precision | Device | Result | Platform | Inference / load | |
|---|---|---|---|---|---|
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 201 ms / 3421 ms |
FP32 | cpu | Passed | Very fast | macos · aarch64 | 46 ms / 3808 ms |
Test setup & sample details
- Quality gate
- Every English, Chinese, and Spanish case must return finite normalized non-degenerate distributions and the checked-in expected choice/yes-no result or ordered-score interval.
- Tested
- 2026-11-14T10:47:51.246409+00:00
- Environment
- Apple M3 Max · macOS 27.2 · PyTorch 2.11.0 · Laya 0.4.31
- Runtime
- pytorch 2.11.0
- Artifact revision
- 1c5edc17a7acd8701df6fc341c0d179f1c62c982
- Fixture
{ "file": "model-samples/open-jev-laya-multilingual.json", "url": "https://f005.backblazeb2.com/file/hubters-webai-public/assets/benchmarks/open-jev-laya-multilingual.json", "size": 1368, "sha1": "ff4a5039dbc0c37a52717f0c82420ff45e0a2803", "source": "WebAI-authored multilingual regression cases with unambiguous gold labels.", "license": "CC0-1.0", "licenseUrl": "https://creativecommons.org/publicdomain/zero/1.0/", "preprocessing": "Pinned mmBERT tokenizer; each question/options prefix uses Laya's marker format and the shared state is truncated to the remaining context.", "sha256": "6a3f2aa202760f49daa8e9da5d88f33b018598b63fac8060d25d09b3b18dadd4" }- Rerun when
- checkpoint; SDK; Torch; fixture; device
Per-case quality & failure details
[
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"checks": [
true,
true
]
},
"runtime": {
"acceleration": "cpu",
"artifactRevision": "1c5edc17a7acd8701df6fc341c0d179f1c62c982",
"cpuThreads": 4,
"device": "cpu",
"durationMs": 46.345584,
"engine": "pytorch",
"fallback": false,
"fallbackReason": null,
"family": {
"catalogId": "laya-native",
"defaultModelId": "laya-multilingual-native",
"displayName": "Laya Desktop",
"id": "laya",
"variantId": "multilingual",
"variantName": "Multilingual"
},
"inferenceMs": 46.11308401217684,
"loadMs": 3807.576792,
"modelId": "laya-multilingual-native",
"mpsAllocatedBytes": null,
"precision": "fp32",
"provider": "PyTorch CPU",
"requestedDevice": "cpu",
"requestedPrecision": "fp32",
"reused": false,
"selectionReason": "Explicit device selection",
"version": "2.11.0",
"totalMs": 3853.6898760121767,
"grade": "good",
"questionsPerSecond": 43.37163828539142
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"checks": [
true,
true
]
},
"runtime": {
"acceleration": "mps",
"artifactRevision": "1c5edc17a7acd8701df6fc341c0d179f1c62c982",
"cpuThreads": 4,
"device": "mps",
"durationMs": 201.469708,
"engine": "pytorch",
"fallback": false,
"fallbackReason": null,
"family": {
"catalogId": "laya-native",
"defaultModelId": "laya-multilingual-native",
"displayName": "Laya Desktop",
"id": "laya",
"variantId": "multilingual",
"variantName": "Multilingual"
},
"inferenceMs": 201.26191701274365,
"loadMs": 3421.0805830000004,
"modelId": "laya-multilingual-native",
"mpsAllocatedBytes": 1287642368,
"precision": "fp32",
"provider": "PyTorch MPS",
"requestedDevice": "mps",
"requestedPrecision": "fp32",
"reused": false,
"selectionReason": "Explicit device selection",
"version": "2.11.0",
"totalMs": 3622.342500012744,
"grade": "good",
"questionsPerSecond": 9.937299761848946
}
}
]Release validation still required
- Full public dependency backup and forced-public-outage recovery are pending.
- Windows runtime and GPU verification are deferred.