Runs in the browser · Text utilities

Run Piiranha v1 (PII Detection) in your browser

Piiranha v1 (PII Detection) downloads 432.1 MB over WebGPU (q4f16), or 302.5 MB over WebAssembly (uint8), to find personally identifiable information in text entirely in the tab with Transformers.js. No install, no server.

Text utilities · onnx-community/piiranha-v1-detect-personal-information-ONNX

WebGPU download

432.1 MB

q4f16

WASM download

302.5 MB

uint8

Parameters: 278.23M
Pipeline task: token-classification

Reading

The WASM build downloads smaller here: 302.5 MB (uint8) against 432.1 MB (q4f16) for WebGPU. The CPU-fallback quant compresses tighter than the GPU pick for this model.

The quant ladder spans 3.6x: 302.5 MB (uint8) to 1.07 GB (fp32).

Live run this browser

Checking what this browser can run…

All measured variants

Quant Download size

Variant	Size
uint8 WASM pick	302.5 MB
q4f16 WebGPU pick	432.1 MB
fp16	548.6 MB
q8	604.9 MB
bnb4	818.0 MB
q4	823.1 MB
fp32	1.07 GB

Sizes measured from the HuggingFace API file tree for onnx-community/piiranha-v1-detect-personal-information-ONNX, not estimated.

Use it with Transformers.js

import { pipeline } from "@huggingface/transformers";

const pipe = await pipeline("token-classification", "onnx-community/piiranha-v1-detect-personal-information-ONNX", {
  device: "webgpu", // usually falls back to "wasm"; wrap in try/catch for production
  dtype: "q4f16", // use "uint8" for the WASM build
});

const result = await pipe(/* your input */);

Requires npm install @huggingface/transformers (or the CDN build).

Embed this

A live badge for your model card or README: 432.1 MB over WebGPU, updated as the data is.

Markdown

[![Piiranha v1 (PII Detection) in browser](https://localmodel.run/badge/browser/piiranha-v1/size.svg)](https://localmodel.run/browser/piiranha-v1)

HTML

<a href="https://localmodel.run/browser/piiranha-v1"><img src="https://localmodel.run/badge/browser/piiranha-v1/size.svg" alt="Piiranha v1 (PII Detection) in browser" /></a>

Sources

huggingface.co

Same job, different size

← Punctuate All 413.1 MB

FAQ

WebGPU or WASM for Piiranha v1 (PII Detection), in practice?

Chrome, Edge, and Safari 26+ run the WebGPU build (q4f16) on the GPU. Firefox has WebGPU on Windows and Apple Silicon Macs but not everywhere yet. Any browser without a WebGPU adapter falls back automatically to the WebAssembly build (uint8) on CPU: same model, slower to load, slower to run.

What does q4f16 mean for Piiranha v1 (PII Detection)?

The WebGPU build here uses q4f16: 4-bit weights with some layers kept at 16-bit for stability: WebGPU's usual smallest clean build. The WASM fallback uses uint8: 8-bit integers: about a quarter the size of fp32, with a smaller quality trade than 4-bit.

Sizes measured 2026-08-01 from the HuggingFace API. Last validated 2026-09-14. See all browser models or the methodology.