hjLabs AI Playground
Starting the on-device runtime…
OpenMed Disease NER is a 335M-parameter ONNX model that tags spans of text as people, organisations, places or personal identifiers, with character offsets. On this page it runs entirely inside your browser: the 337 MB download comes straight from the Hugging Face repository “onnx-community/OpenMed-NER-DiseaseDetect-BioMed-335M-ONNX” into your browser cache, and every inference after that executes on your own GPU through WebGPU. Expect a download of roughly a minute on a decent connection. It fits comfortably in the browser cache and in the memory of any GPU from the last few years, including laptop integrated graphics. It is an English-language model; expect quality to fall off sharply on other languages.
Disease and condition names only. Narrower than the 84-type biomedical tagger and more confident inside its one category. In practice people reach for a model like this for entity extraction and — more usefully — redacting personal data locally, before anything leaves the machine.
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 23 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 OpenMed Disease NER here is the one-off 337 MB download, and once that is cached the page keeps working with the network switched off.
openmed disease neropenmed disease ner onnxopenmed disease ner browserrun openmed disease ner locallyonnx-community/openmed-ner-diseasedetect-biomed-335m-onnxentity recognition modelopenmed disease ner webgpuopenmed disease ner download sizefree entity recognition modeltransformers.js model
About 337 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. onnx-community/OpenMed-NER-DiseaseDetect-BioMed-335M-ONNX 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.