Your Snapdragon NPU,
as a local AI server.

from openai import OpenAI

client = OpenAI(
    base_url="http://127.0.0.1:18181/v1",
    api_key="calcine_…",  # Server › API keys
)
stream = client.chat.completions.create(
    model="qualcomm/Qwen3-4B",
    messages=[{"role": "user", "content": "Hello from my NPU!"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "http://127.0.0.1:18181/v1",
  apiKey: process.env.CALCINE_API_KEY, // Server › API keys
});
const stream = await client.chat.completions.create({
  model: "qualcomm/Qwen3-4B",
  messages: [{ role: "user", content: "Hello from my NPU!" }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

curl http://127.0.0.1:18181/v1/chat/completions \
  -H "Authorization: Bearer $CALCINE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qualcomm/Qwen3-4B",
    "messages": [{"role": "user", "content": "Hello from my NPU!"}]
  }'