hjLabs AI Playground
Starting the on-device runtime…
NLLB-200 Distilled 600M is a 600M-parameter ONNX model that translates text between languages with an encoder-decoder transformer. On this page it runs entirely inside your browser: the 917 MB download comes straight from the Hugging Face repository “Xenova/nllb-200-distilled-600M” into your browser cache, and every inference after that executes on your own GPU through WebGPU. This is a serious download — do it once on a connection you are not paying by the megabyte for. Once it is in the Cache Storage API it stays there, and subsequent visits load it from disk in seconds. The model is multilingual, so it is not restricted to English input.
One model, 200 languages, any direction — including low-resource pairs nothing else covers. Costs ~900 MB of cache. In practice people reach for a model like this for translating notes, documents and UI strings privately, including material you are not allowed to paste online.
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. Hugging Face records about 10k downloads a month. It is a specialist choice rather than a default, which is exactly why it is worth trying when the popular model gets your particular input wrong.
Because there is no inference server behind this page, there is nothing to rate-limit and nothing to bill: the only cost of running NLLB-200 Distilled 600M here is the one-off 917 MB download, and once that is cached the page keeps working with the network switched off.
nllb-200 distilled 600mnllb-200 distilled 600m onnxnllb-200 distilled 600m browserrun nllb-200 distilled 600m locallyxenova/nllb-200-distilled-600mtranslation modelnllb-200 distilled 600m webgpunllb-200 distilled 600m download sizefree translation modeltransformers.js model
About 917 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/nllb-200-distilled-600M 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.