hjLabs AI Playground
Starting the on-device runtime…
all-MiniLM-L6-v2 is a 22.7M-parameter ONNX model that turns text into a dense vector whose distances encode meaning. On this page it runs entirely inside your browser: the 91 MB download comes straight from the Hugging Face repository “Xenova/all-MiniLM-L6-v2” 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 default sentence embedder everywhere: 384 dimensions, tiny, fast, and good enough for most retrieval. In practice people reach for a model like this for semantic search, deduplication, clustering and retrieval-augmented generation — all with a local index.
Available precisions: fp32 (full precision) and q8 (8-bit). fp32 comes first because at this size full precision is both the fastest WebGPU path and the best quality; the quantized variant exists for the WebAssembly fallback and for tight cache budgets. It is this playground's default pick for the task, and Hugging Face records about 2.6M 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 all-MiniLM-L6-v2 here is the one-off 91 MB download, and once that is cached the page keeps working with the network switched off.
all-minilm-l6-v2all-minilm-l6-v2 onnxall-minilm-l6-v2 browserrun all-minilm-l6-v2 locallyxenova/all-minilm-l6-v2embeddings modelall-minilm-l6-v2 webgpuall-minilm-l6-v2 download sizefree embeddings modeltransformers.js model
About 91 MB for the fp32 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/all-MiniLM-L6-v2 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.