Free · runs in your browser · no sign-up
Learn how LLMs work by running one in your browser
Chat with a small language model on your own GPU, or plug in any OpenAI-compatible API. Then look inside: the system prompt, the tokens, the context window, every tool call and how fast it thinks.
- WebGPU, on your machine
- 5 models ≤ 2B
- Any OpenAI-compatible API
- youWhat is 23 × 19?
- model
<tool_call>{"name":"calculator","arguments":{"expression":"23*19"}}</tool_call> - toolcalculator →
437 - answer23 × 19 = 437
Inside the model
What you'll see that chat apps hide
-
The system prompt
Edit the hidden instructions and see the full prompt the model actually receives, tool definitions included.
-
Tokens and the context window
A live meter shows how many tokens your conversation uses and how much room is left.
-
Function calling
Give the model a calculator, a clock, Wikipedia or your own JavaScript tool, and watch it decide when to use them.
-
The agent loop, step by step
Prompt → model → tool call → result → answer, with the raw text and JSON behind each step.
-
Speed: prefill vs decode
How fast the model reads your prompt, and how fast it writes. In tokens per second, live.
-
Private by default
Local models run entirely on your GPU. Tool code runs in a locked-down sandbox. No account, no server, and your API key never leaves your browser.
How it works
Three steps, no setup
-
Pick a model
One of 5 small models (0.6B–1.7B parameters) downloaded once into your browser, or any OpenAI-compatible API such as OpenAI or Ollama.
-
Ask something
Change the system prompt, switch tools on or off, or write your own tool with a JSON Schema and a few lines of JavaScript.
-
Watch what happens
Follow every step of the loop, and see the context window and tokens per second update as the model generates.
Learning path · 8 lessons · 27 min total
Learn the concepts
-
01
What is a token?
Models read pieces of words mapped to numbers, not words. -
02
Temperature, top-p and top-k
How the model picks one next token out of thousands of options. -
03
The context window
The model's working memory, and what happens when it fills up. -
04
Managing the context window
Dropping, trimming and summarizing: how chat apps make room, and what each one forgets. -
05
The system prompt
The hidden instructions sent before every conversation. -
06
How function calling works
A model can only write text. Here is how that text becomes a tool call. -
07
Prefill vs decode
The two speeds of every LLM: reading your prompt and writing the answer. -
08
Run an LLM in your browser
WebGPU, small models, and what to expect from a 1B model on your laptop.
FAQ
Questions
Is it free?
Yes. It runs in your browser and the code is on GitHub. Local models cost nothing to run. If you connect a paid API, you pay that provider directly.
What do I need to run a model locally?
A browser with WebGPU (recent Chrome or Edge) and roughly 1–2 GB of free GPU memory. The model downloads once and is cached.
Is my data sent anywhere?
With a local model, nothing leaves your computer. With an API, your messages go only to the API address you enter, and your key is never saved: you enter it each visit.
Which models can I use?
Locally: Qwen3 0.6B, Llama 3.2 1B, Qwen2.5 1.5B, SmolLM2 1.7B and Qwen3 1.7B. Remotely: any model behind an OpenAI-compatible /chat/completions endpoint.
See what an LLM is actually doing
Load a model, ask a question, and watch every step. It takes about a minute.