hjLabs AI Playground
Starting the on-device runtime…
BERT Base Uncased is a 110M-parameter ONNX model that predicts the tokens that belong in a masked position in a sentence. On this page it runs entirely inside your browser: the 112 MB download comes straight from the Hugging Face repository “Xenova/bert-base-uncased” into your browser cache, and every inference after that executes on your own GPU through WebGPU. That is a one-off download of well under a minute on a normal connection, and small enough that integrated graphics handle it without complaint. It is an English-language model; expect quality to fall off sharply on other languages.
The original masked language model. Its guesses are the clearest window into what a 2018 LM actually learned. In practice people reach for a model like this for probing what a language model has actually learned, and a genuinely useful teaching demo for masked pretraining.
Available precisions: q8 (8-bit) and fp32 (full precision). q8 comes first because it roughly halves the download at a quality cost you will struggle to measure on this class of model; fp32 is there when you want the reference numbers. It is this playground's default pick for the task, and Hugging Face records about 5k downloads a month for the repository — a good sign that it is maintained and that the ONNX export is not abandoned.
Because there is no inference server behind this page, there is nothing to rate-limit and nothing to bill: the only cost of running BERT Base Uncased here is the one-off 112 MB download, and once that is cached the page keeps working with the network switched off.
bert base uncasedbert base uncased onnxbert base uncased browserrun bert base uncased locallyxenova/bert-base-uncasedfill-mask modelbert base uncased webgpubert base uncased download sizefree fill-mask modeltransformers.js model
About 112 MB for the q8 build, including the tokenizer and config files the runtime also has to fetch — this is the whole payload, not just the weights file. It is downloaded once and then served from the browser Cache Storage API.
Yes, through the WebAssembly fallback, which is slower but works anywhere. WebGPU (Chrome or Edge 113+, Safari 26+) is what makes it feel interactive. On WASM, prefer the smaller quantized build.
No. Xenova/bert-base-uncased is a public repository, so your browser fetches the ONNX files directly over HTTPS. There is no account, no key and no server in between.
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.