hjLabs AI Playground
Starting the on-device runtime…
Llama 3.2 1B Instruct is a 1.2B-parameter ONNX model that generates text a token at a time in response to a prompt, streaming its reply as it decodes. On this page it runs entirely inside your browser: the 1.7 GB download comes straight from the Hugging Face repository “onnx-community/Llama-3.2-1B-Instruct-ONNX” into your browser cache, and every inference after that executes on your own GPU through WebGPU. This is one of the largest models the playground offers, so treat the first load as a deliberate decision rather than something to try on mobile data. It wants a discrete GPU with headroom, and it is worth requesting persistent storage before you start so the browser does not evict it later. The model is multilingual, so it is not restricted to English input.
Meta’s smallest Llama 3.2. Heaviest download here at ~1.7 GB; pick it if you want familiar Llama behaviour. In practice people reach for a model like this for drafting, rewriting, summarising a pasted passage, or simply having a conversation that no server ever sees.
Available precisions: q4 (4-bit) and q8 (8-bit). q4 comes first because ONNX Runtime executes 4-bit block-quantised matmuls natively on WebGPU, which is what makes decoding fast enough to be usable — it is a speed choice at least as much as a size one. Hugging Face records about 2k 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 Llama 3.2 1B Instruct here is the one-off 1.7 GB download, and once that is cached the page keeps working with the network switched off.
llama 3.2 1b instructllama 3.2 1b instruct onnxllama 3.2 1b instruct browserrun llama 3.2 1b instruct locallyonnx-community/llama-3.2-1b-instruct-onnxchat modelllama 3.2 1b instruct webgpullama 3.2 1b instruct download sizefree chat modeltransformers.js model
About 1.7 GB for the q4 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/Llama-3.2-1B-Instruct-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.