Skip to content
BYOK Tools

WebLLM Chat

Chat with LLMs running entirely in your browser via WebGPU.

3.9 editor score•Local AI•Free & open source

Overview

WebLLM Chat runs quantized open models such as Llama, Qwen and Phi directly in the browser using WebGPU, with no server. Models are cached locally after the first download.

  • WebGPU inference
  • No install
  • Offline after download
  • Custom model URLs

Our verdict

What we like

  • Truly zero setup
  • Private

Watch out for

  • Needs a WebGPU-capable GPU
  • Small models only

Works with these providers

Keys from these providers work in this app. Usage is billed by the provider at its list price.

BYOK Key Safety Score

Key handling in WebLLM Chat

How we score
92/ 100

Grade A

Your key is stored on your device and requests go directly to the provider.

  • Key storage

    Key stays on your device; requests go direct to the provider.

    40/40
  • Auditable code

    Open source: anyone can verify how keys are handled.

    25/25
  • Self-hosting

    Can run entirely on your own infrastructure.

    15/15
  • Offline option

    Supports local models, so no key is needed at all for private work.

    10/10
  • Provider choice

    1 provider option, which lets you pick the provider whose data terms you trust.

    2/10

Whatever the score, give each app its own key, set a monthly spend limit with your provider, and revoke keys you no longer use. Read the key-safety checklist.

WebLLM Chat FAQ

Does WebLLM Chat support bring your own key?
Yes. WebLLM Chat accepts your own API key from OpenAI-compatible. Usage is billed by the provider at its API rates.
Where does WebLLM Chat store my API key?
On your device. Requests go directly from WebLLM Chat to the provider. Its BYOK Tools Key Safety Score is 92/100.
Is WebLLM Chat free?
Open source: Free & open source. API usage is billed separately by your model provider.
Is WebLLM Chat open source?
Yes. The source code is at https://github.com/mlc-ai/web-llm-chat. It can also be self-hosted.
Can WebLLM Chat run local models?
Yes. It can connect to local runtimes such as Ollama or LM Studio, so no API key is needed for private or offline use.
Which platforms does WebLLM Chat support?
Web.

Community reviews

No reviews yet.