yolact-resnet50 — LiteRT.js demo

Source	https://huggingface.co/litert-community/YOLACT-ResNet50-LiteRT
License	mit
Model file	`de20dcdb186be71368cbd668fd62e71e6089d0c94c100968975cfc6300c25a83.tflite` — downloaded from the source at runtime; this site hosts no weights

Run it in your browser

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.

Backend	Status	Full delegation	Output match	Latency p50 (ms)	Environment	Verified	Provenance
`wasm_xnnpack`	pass	—	—	1700.407	mac-studio-m4-max · chromium 151.0.7922.34 headless · macOS · @litertjs/core 2.5.3	2026-08-11	measured
`webgpu_mldrift`	pass	yes	pass	63.108	mac-studio-m4-max · chromium 151.0.7922.34 headless · macOS · @litertjs/core 2.5.3	2026-08-11	measured

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 yolact-resnet50: load the model from https://huggingface.co/litert-community/YOLACT-ResNet50-LiteRT/resolve/main/de20dcdb186be71368cbd668fd62e71e6089d0c94c100968975cfc6300c25a83.tflite (license: mit) 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 yolact-resnet50 with the sweep harness: write /tmp/catalog.csv with the header line model_id,source,input_spec,license,notes and the single row yolact-resnet50,https://huggingface.co/litert-community/YOLACT-ResNet50-LiteRT/resolve/main/de20dcdb186be71368cbd668fd62e71e6089d0c94c100968975cfc6300c25a83.tflite,1x3x550x550:float32,mit, — then run: cd web/sweep && npm ci && npm run sweep -- --catalog /tmp/catalog.csv --out out/ — and compare out/yolact-resnet50.json with the sweep table on this page.