Run an LLM model locally through Ollama

[samshdn]

After installing the model, we can use it in two ways：

Approach 1: ollama UI:

example:
ollama run qwen3:4b "What is the capital of Brazil? /no_think"

Approach 2: API

example:

const payload = {
  "model": "qwen3:4b",
  "prompt": "What is the capital of Brazil? /think",
  "stream": false
}

const response = await fetch("http://localhost:11434/api/generate", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify(payload),
});

const data = await response.json();
console.log(JSON.stringify(data))

The UI is well-suited for simple interactions., some batch operations can be performed using the API.