Web LLM

Give an AI node a chat model that runs inside your browser: free, private, offline once downloaded, and no API key.

Try it

workflow · explain-eli5.awf 4 étapes

Explain Like I'm 5 : un workflow de 4 étapes, qui commence par Right-click a selection et se termine par Show the explanation.

1. 1 Right-click a selection(Context Menu — ouvrir sa page de documentation) Context Menu
2. 2 Get selected text(Action dans la page — ouvrir sa page de documentation) Action dans la page
3. 3 Explain simply(Basic LLM Chain — ouvrir sa page de documentation) Basic LLM Chain + Local AI model
4. 4 Show the explanation(Display Markdown — ouvrir sa page de documentation) Display Markdown

Ouvrir dans AWFlow Copier le .awf

What it does

Web LLM is a model you plug into the Model slot of an AI node, such as the Tools Agent or Basic LLM Chain. It does not run on its own and has no output. When the AI node runs, the model answers on your device, using your graphics card through WebGPU.

• The model downloads the first time you use it, then stays in the browser. Installed models start right away.
• It loads and runs in the background, so the page stays responsive. The run log shows the loading progress.
• Temperature is 0.5 by default.
• It works with the Tools Agent: the tools are described in the prompt and the model writes its tool calls in its reply. The common formats (<tool_call>…</tool_call>, [TOOL_CALLS], fenced JSON, or a reply that is only the JSON call) are all understood. Instruct models trained for tool use do this much better than very small ones.

When to use it

• Private text that must not leave your computer.
• Workflows that must work offline, or without paying for an AI service.
• Short, simple jobs: rewrite, tag, extract, short summaries.

For bigger models, use Ollama. On a device without WebGPU, use Transformers Chat.

Inputs and settings

Réglage	Type	Ce que cela fait
Model	Model picker	The in-browser model to run. Installed models are ready immediately; others download on first use — or install them from Local Models.
Options	Group	The options to use with the model.
Options › Temperature	Number	The temperature to use for the model. Par défaut : 0.5

The Model picker shows which models are installed and lets you download one inline. A new node starts with the local model you chose as your default. To install, compare or delete models ahead of time, use the Local Models page.

When you publish or share the workflow, Model is cleared, so whoever installs it picks a model on their own device.

Outputs

This node has no output port. It plugs into a slot on another node instead of passing items along.

• Model slot of Tools Agent, Q&A Agent, RAG Agent, Basic LLM Chain, Indexer, Text Classifier, Sentiment Analysis, Summarization, Information Extractor, Guardrails, Auto-fixing Output Parser

The AI node you connect it to produces the output. Web LLM only decides which model answers.

Dependencies and credentials

None. This node needs no connection and has no slots for other nodes.

Example workflow

1. A Context Menu trigger on selected text.
2. Basic LLM Chain with Prompt Rewrite this to sound more professional: {{ $input.selectionText }}.
3. Web LLM in its Model slot, with an installed model.
4. Clipboard Write with Text {{ $input.response }}.

Common issues

• “Model parameter is required and cannot be empty”. Pick a model in Model.
• “Invalid model ID: …”. The model is not in this browser’s model list, for example after importing a workflow from another device. Pick a model again.
• The first run takes minutes. The model is downloading (often hundreds of MB to a few GB). Install it in advance from Local Models.
• It fails on this computer. Your browser or graphics card has no WebGPU support. Use Transformers Chat or a cloud model.
• The agent never calls a tool. Small models often answer in plain text instead. Use a larger instruct model, and give your tools clear descriptions.

Recipes with this node

Turn highlighted text into a Todoist task débutant · 6 min Nécessite une connexion Explain any highlighted text in plain words débutant · 4 min Sur l'appareil Summarize the page you're reading, on your device débutant · 5 min Sur l'appareil Rewrite rough text in a professional tone débutant · 4 min Sur l'appareil

Related nodes

• Transformers Chat: small on-device chat that also works without WebGPU.
• Ollama: larger local models through the Ollama app.
• Chrome AI: the model built into Chrome.
• Tools Agent: an agent that can use tools and memory.