Skip to content

Runs in the browser · Text generation

Run SmolLM2-135M-Instruct in your browser

SmolLM2-135M-Instruct downloads 112.2 MB over WebGPU (q4f16), or 130.8 MB over WebAssembly (uint8), to generate text entirely in the tab with Transformers.js. No install, no server.

Text generation · HuggingFaceTB/SmolLM2-135M-Instruct

WebGPU download
112.2 MB
q4f16
WASM download
130.8 MB
uint8
Parameters
134.5M
Pipeline task
text-generation

Reading

The smallest text generation download in the catalog (112.2 MB).

The quant ladder spans 4.6x: 112.2 MB (q4f16) to 515.3 MB (fp32).

Run it in your browser

Live run this browser

Checking what this browser can run…

All measured variants

Quant Download size
Variant Size
q4f16 WebGPU pick 112.2 MB
uint8 WASM pick 130.8 MB
bnb4 167.3 MB
q4 173.6 MB
fp16 257.7 MB
q8 261.6 MB
fp32 515.3 MB

Sizes measured from the HuggingFace API file tree for HuggingFaceTB/SmolLM2-135M-Instruct, not estimated.

Use it with Transformers.js

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

const pipe = await pipeline("text-generation", "HuggingFaceTB/SmolLM2-135M-Instruct", {
  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).

Sources

Same job, different size

FAQ

WebGPU or WASM for SmolLM2-135M-Instruct, 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 SmolLM2-135M-Instruct?

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 2026-08-03. See all browser models or the methodology.