Qwen3-8B-GGUF API (8-Bit)

Overview

This Hugging Face Space exposes the Qwen3-8B-GGUF (8-Bit Precision) model as a simple REST API. Send a POST request to /generate with your message and receive an AI-generated response.

Endpoints

Request Body — POST /generate

Send a JSON body with the following fields:

Prompt Construction

The API constructs the prompt sent to the model as follows:

{instructions}
{user} said {message}

For example, if you send:

{"instructions": "idk", "message": "thisissupermario", "user": "admin"}

The model receives:

idk
admin said thisissupermario

Code Examples

# Python — requests
import requests

url = "http://dreamlongyt-agent.hf.space/generate"
payload = {
    "instructions": "idk",
    "message": "thisissupermario",
    "user": "admin"
}

response = requests.post(url, json=payload)
print(response.json())

# cURL
curl -X POST "http://dreamlongyt-agent.hf.space/generate" \
     -H "Content-Type: application/json" \
     -d '{"instructions":"idk","message":"thisissupermario","user":"admin"}'

// JavaScript — fetch
const response = await fetch("http://dreamlongyt-agent.hf.space/generate", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    instructions: "idk",
    message: "thisissupermario",
    user: "admin"
  })
});
const data = await response.json();
console.log(data);

Response

The API returns a JSON object with the following fields:

Interactive Docs

You can also explore and test the API interactively via the built-in Swagger UI at http://dreamlongyt-agent.hf.space/docs.