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.

Liquid LFM3 1.7B Base

Continue a literal text or code prefix locally with the pretrained Liquid LFM3 1.7B Base checkpoint.

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

Continue a literal text or code prefix locally with the pretrained Liquid LFM3 1.7B Base checkpoint.

Created by
Liquid AI
Model released
Unknown
Source repository created
Oct 26, 2026
Model weights · Q4F16
1.5 GB

Best for

  • Short prose continuation
  • Short code continuation

Keep in mind

  • Short single-sequence text and code continuation only. Review generated facts or code.
  • The browser recomputes the full prefix and limits combined length to 128 tokens.
  • WebGPU uses CPU operators alongside GPU compute. WASM requires eight threads in a cross-origin isolated page.
  • Only short English and Python continuations were evaluated.
  • The model license limits commercial use based on annual revenue.

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/LiquidAI/LFM3-1.7B-Base
Release verification
Unknown
Release evidence
The official model card identifies this exact checkpoint. The retained repository creation time does not establish its public release date.
Source updated
Nov 3, 2026
Browser model files
LocalAI/lfm3-1.7b-base-onnx
Files updated
Nov 15, 2026
Artifact revision
30d656347623355f1574d986727e569a88897539

Input

TEXT

Sample result

Liquid LFM3 1.7B Base

Settings

Limits the number of newly generated continuation tokens. Lower limits can cut off the continuation. Higher limits take more time and memory.

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.

Liquid LFM3 1.7B Base

6 configurations tested
Passed6
Failed0
TestedNov 15, 2026
RuntimeONNX Runtime Web 1.31.0-dev.20260914-8d85527a0

Quality criteria

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

PrecisionDeviceResult
Q4F16GPU · WebGPUAcceleratedPassedSlow
Q4F16GPU · WebGPUAcceleratedPassedSlow
Q4F16GPU · WebGPUAcceleratedPassedSlow
Q4F16CPU · WASMPassedVery slow
Q4F16CPU · WASMPassedVery slow
Q4F16CPU · WASMPassedVery slow
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-15T21:46:44.754Z
Environment
Chrome 157 on macOS 27.2, Apple M3 Max. WebGPU with CPU operators or eight-thread WASM in cross-origin isolation.
Runtime
ONNX Runtime Web 1.31.0-dev.20260914-8d85527a0
Artifact revision
30d656347623355f1574d986727e569a88897539
Fixture
{
  "file": "model-samples/lfm3-1.7b-base/base-completion-fixtures.json",
  "size": 267,
  "sha1": "30bb1eee6b45d542a81bcc346b916acab19963fd",
  "sha256": "69694e5c4aee2a31ce0cc92b48444d0d8f1866426d4b36afa413ac5f57f593f9"
}
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": "expectedPrefixMatch",
      "score": 1,
      "passed": true
    },
    "runtime": {
      "durationMs": 1760.7800000309944,
      "device": "webgpu",
      "loadMs": 3996.929999947548,
      "inferenceMs": 1760.9599999785423,
      "totalMs": 5757.88999992609,
      "gpuDispatches": 20172,
      "tokensPerSecond": 6.814464837444475,
      "grade": "fast",
      "engine": "ONNX Runtime Web",
      "version": "1.31.0-dev.20260914-8d85527a0",
      "artifactRevision": "30d656347623355f1574d986727e569a88897539"
    }
  },
  {
    "precision": "q4f16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "metric": "expectedPrefixMatch",
      "score": 1,
      "passed": true
    },
    "runtime": {
      "durationMs": 1796.4750000238419,
      "device": "webgpu",
      "loadMs": 3996.929999947548,
      "inferenceMs": 1796.5049999952316,
      "totalMs": 5793.4349999427795,
      "gpuDispatches": 20172,
      "tokensPerSecond": 6.679636293821532,
      "grade": "fast",
      "engine": "ONNX Runtime Web",
      "version": "1.31.0-dev.20260914-8d85527a0",
      "artifactRevision": "30d656347623355f1574d986727e569a88897539"
    }
  },
  {
    "precision": "q4f16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "metric": "expectedPrefixMatch",
      "score": 1,
      "passed": true
    },
    "runtime": {
      "durationMs": 1822.1399999856949,
      "device": "webgpu",
      "loadMs": 3996.929999947548,
      "inferenceMs": 1822.1699999570847,
      "totalMs": 5819.099999904633,
      "gpuDispatches": 20172,
      "tokensPerSecond": 6.585554586170677,
      "grade": "fast",
      "engine": "ONNX Runtime Web",
      "version": "1.31.0-dev.20260914-8d85527a0",
      "artifactRevision": "30d656347623355f1574d986727e569a88897539"
    }
  },
  {
    "precision": "q4f16",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "metric": "expectedPrefixMatch",
      "score": 1,
      "passed": true
    },
    "runtime": {
      "durationMs": 7963.260000050068,
      "device": "wasm",
      "loadMs": 3160.3150000572205,
      "inferenceMs": 7963.425000011921,
      "totalMs": 11123.740000069141,
      "gpuDispatches": 0,
      "tokensPerSecond": 1.5068893095598987,
      "grade": "acceptable",
      "engine": "ONNX Runtime Web",
      "version": "1.31.0-dev.20260914-8d85527a0",
      "artifactRevision": "30d656347623355f1574d986727e569a88897539"
    }
  },
  {
    "precision": "q4f16",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "metric": "expectedPrefixMatch",
      "score": 1,
      "passed": true
    },
    "runtime": {
      "durationMs": 7447.935000002384,
      "device": "wasm",
      "loadMs": 3160.3150000572205,
      "inferenceMs": 7447.954999983311,
      "totalMs": 10608.270000040531,
      "gpuDispatches": 0,
      "tokensPerSecond": 1.6111805186828987,
      "grade": "acceptable",
      "engine": "ONNX Runtime Web",
      "version": "1.31.0-dev.20260914-8d85527a0",
      "artifactRevision": "30d656347623355f1574d986727e569a88897539"
    }
  },
  {
    "precision": "q4f16",
    "device": "wasm",
    "status": "pass",
    "quality": {
      "metric": "expectedPrefixMatch",
      "score": 1,
      "passed": true
    },
    "runtime": {
      "durationMs": 7871.849999964237,
      "device": "wasm",
      "loadMs": 3160.3150000572205,
      "inferenceMs": 7871.870000004768,
      "totalMs": 11032.185000061989,
      "gpuDispatches": 0,
      "tokensPerSecond": 1.5244154184447571,
      "grade": "acceptable",
      "engine": "ONNX Runtime Web",
      "version": "1.31.0-dev.20260914-8d85527a0",
      "artifactRevision": "30d656347623355f1574d986727e569a88897539"
    }
  }
]

Something not quite right?

Tell us what happened with Liquid LFM3. 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.