About this project

This playground is built by hjLabs.in, an independent maker of privacy-first web tools. It exists because the interesting part of open-source AI is no longer getting a model to run — it is getting one to run somewhere that does not cost money per request and does not require trusting a third party with your data. Everything here is a thin, honest interface over @huggingface/transformers, WebLLM and kokoro-js talking to the browser WebGPU API. There is no backend inference, no telemetry on your inputs, and no model claimed to work that has not actually been loaded and run.

hjlabs ai playgroundabout browser aiclient side ai projectprivacy first ai toolsopen source model playgroundwebgpu demo site

Frequently asked questions

Who runs this and how is it funded?

hjLabs.in, an independent maker of web tools. It costs us almost nothing to run because there is no inference server — the site is static files on Cloudflare’s edge and your GPU does all the work, so there is no per-user cost to recover.

Is it really free, and is there a usage limit?

It is free and there is no per-request limit, because we are not paying for the compute — your own GPU is. The only cost is the one-time model download, which your browser caches.

Do I need an account or an API key?

No. There is no sign-up, no key and no quota, because there is no server doing the work — your browser fetches public model files from Hugging Face over HTTPS and runs them on your own GPU.

Can I use the output commercially?

That depends on the individual model, not on this site. Each model page links to its Hugging Face repository, where the licence is stated — most of the catalog is Apache-2.0 or MIT, a few are research-only. We add nothing on top: hjLabs.in claims no rights over anything you produce here.

Is my data uploaded to a server?

No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.

Explore the rest of the playground

Guides, comparisons & alternatives

Model catalog — The model catalog: what actually runs in a browser
WebGPU vs WASM — WebGPU vs WebAssembly for running models in a browser
Browser AI vs cloud API — Browser inference vs a hosted API: an honest comparison
Transformers.js vs WebLLM — Transformers.js vs WebLLM
Whisper model sizes — Choosing a Whisper size for browser transcription
fp32 vs q8 vs q4 — Picking a quantization level for browser inference
Biggest browser LLM — How big a model can a browser tab actually run?
Why no image generation — Why this playground has no text-to-image generation
MedGemma in the browser — MedGemma in the browser: why it does not work, and what does
Free alternatives to paid AI tools — Free, local alternatives to paid AI services
remove.bg alternative — A remove.bg alternative that never uploads your image
Ollama alternative — An Ollama alternative that installs nothing
Open WebUI alternative — An Open WebUI alternative with no server behind it
Whisper API alternative — A Whisper API alternative that runs on your machine
Embeddings API alternative — An embeddings API alternative that costs nothing per token
FAQ — Frequently asked questions about browser-based AI

This playground needs JavaScript and WebGPU. Models are downloaded to your browser and executed on your own GPU, so there is nothing to show without a script engine. Enable JavaScript, or read the FAQ for what the site does.