Run a supported chat model in your browser with on-device response generation after setup.
Start a conversation with your private offline AI assistant. Everything runs locally in your browser.
Llama-3.2-1B-Instruct
Browser + WebGPU
1.5GB+
Local browser storage
100% client-side processing
Disclaimer
This AI assistant runs locally in your browser and may have limitations compared to cloud-based AI services. Responses are generated by a quantized model and should be verified for accuracy. This tool is for informational purposes and should not be used for critical decisions without human verification.
Explore local language-model chat without sending prompts to a hosted inference API. The browser must first load the selected model and its runtime. Performance and model availability depend on the device's memory and supported browser features.
After initialization, ask the model to rewrite a short sample paragraph and compare its response with the original.
Initial setup requires downloads, and offline reuse depends on cached assets. WebGPU support and sufficient device memory are required; responses can be inaccurate.
Use a compatible browser and initialize an available model. Wait for the model assets to download and load. Send a prompt and review the response generated on your device.
Initial setup requires downloads, and offline reuse depends on cached assets. WebGPU support and sufficient device memory are required; responses can be inaccurate.
No registration, no tracking of your content, no server uploads. Don't just take our word for it:
Your files and text are processed entirely on your device. Nothing is ever sent to us.
Once loaded, this tool keeps working with your Wi-Fi turned off. Try it.
Open your browser's DevTools → Network tab. You'll see zero requests carrying your data.
Discover other powerful utilities designed to supercharge your workflow and boost productivity.
Combine PDF files in the order you choose and download one consolidated document.
Merge several PDFs into a single document with browser-local file processing.
Render Markdown and export a PDF with adjustable document settings.