← all models

gliner2.5-multi__gliner25_multi_s128_wfp16

token-classification · family: gliner2.5-multi

Sourcehttps://huggingface.co/litert-community/GLiNER2.5-Multi-LiteRT
Licenseapache-2.0
Model filegliner25_multi_s128_wfp16.tflite — downloaded from the source at runtime; this site hosts no weights

Run it in your browser

—backend actually in use
—live latency p50

Preparing…

Measured sweep results

Every number is labeled with the environment that produced it — headless desktop Chromium is not a user’s phone, and results are only meaningful together with their environment.

BackendStatusFull delegationOutput matchLatency p50 (ms)EnvironmentVerifiedProvenance
wasm_xnnpackpass——1308.485mac-studio-m4-max · chromium 151.0.7922.34 headless · macOS · @litertjs/core 2.5.32026-10-02 stale — latest known 2.6.0measured
webgpu_mldriftoutput_mismatchyesfail21.68mac-studio-m4-max · chromium 151.0.7922.34 headless · macOS · @litertjs/core 2.5.32026-10-02 stale — latest known 2.6.0measured

Full record (failure class, evidence, sweep config): raw sweep JSON · card.json · CARD.md

Build this yourself

One-line prompt for your AI coding assistant (uses the litert-cookbook web skill):

Use the litert-cookbook web skill to build a LiteRT.js browser demo for gliner2.5-multi__gliner25_multi_s128_wfp16: load the model from https://huggingface.co/litert-community/GLiNER2.5-Multi-LiteRT/resolve/main/gliner25_multi_s128_wfp16.tflite (license: apache-2.0) and run it with @litertjs/core.

Reproduce this with an agent

One-line prompt for Claude Code / Gemini CLI — re-runs the same sweep verification for this model, locally:

In the edge-compat repo, verify gliner2.5-multi__gliner25_multi_s128_wfp16 with the sweep harness: write /tmp/catalog.csv with the header line model_id,source,input_spec,license,notes and the single row gliner2.5-multi__gliner25_multi_s128_wfp16,https://huggingface.co/litert-community/GLiNER2.5-Multi-LiteRT/resolve/main/gliner25_multi_s128_wfp16.tflite,1x128x768:float32;1x128:float32;1x48x128:float32;1x5x128:float32;1x48:float32,apache-2.0, — then run: cd web/sweep && npm ci && npm run sweep -- --catalog /tmp/catalog.csv --out out/ — and compare out/gliner2.5-multi__gliner25_multi_s128_wfp16.json with the sweep table on this page.