Text utilities in the browser

Every text utilities model, ranked by WebGPU size

Sizes measured from the HuggingFace API file tree for each model's repo, not estimated. Sorted smallest to largest by the WebGPU headline pick.

Size ladder

A bytes-per-parameter comparison needs at least 3 models with a verified parameter count and a real spread between them; this group does not clear that bar yet.

Use it with Transformers.js

Every text utilities model here shares the same pipeline() task, so one snippet covers the group. This one loads GLiNER Small v2.1, the smallest download; swap the repo string for any other row in the table above.

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

const pipe = await pipeline("token-classification", "onnx-community/gliner_small-v2.1", {
  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).

Notable text utilities models

Other tasks

Or see every browser model grouped by task, or the main GGUF catalog for native runtimes outside the browser.

FAQ