hjLabs AI Playground
Starting the on-device runtime…
YOLOS Tiny is a 6.5M-parameter ONNX model that finds objects in an image and returns a labelled bounding box and confidence score for each. On this page it runs entirely inside your browser: the 26 MB download comes straight from the Hugging Face repository “Xenova/yolos-tiny” into your browser cache, and every inference after that executes on your own GPU through WebGPU. At this size the download is over before you have finished reading this paragraph, even on a phone tethered to a hotspot, and it costs almost nothing to keep cached alongside a dozen other models.
26 MB and fast enough to track a webcam in real time; misses small or overlapping objects. In practice people reach for a model like this for counting, cropping, auto-tagging photo libraries and running live detection over a webcam feed.
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 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 YOLOS Tiny here is the one-off 26 MB download, and once that is cached the page keeps working with the network switched off.
yolos tinyyolos tiny onnxyolos tiny browserrun yolos tiny locallyxenova/yolos-tinyobject detection modelyolos tiny webgpuyolos tiny download sizefree object detection modeltransformers.js model
About 26 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/yolos-tiny 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.