NVIDIA Nemotron 3 Nano 30B A3B BF16

from openai import OpenAI

# Initialize the OpenAI client with Qubrid base URL
client = OpenAI(
    base_url="https://platform.qubrid.com/v1",
    api_key="QUBRID_API_KEY",
)

# Create a streaming chat completion
stream = client.chat.completions.create(
    model="nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
    messages=[
      {
        "role": "user",
        "content": "Explain quantum computing in simple terms"
      }
    ],
    max_tokens=8192,
    temperature=0.3,
    top_p=1,
    stream=True
)

# If stream = False comment this out
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print("\n")

# If stream = True comment this out
print(stream.choices[0].message.content)

import OpenAI from "openai";

// Initialize the OpenAI client with Qubrid base URL
const client = new OpenAI({
  baseURL: "https://platform.qubrid.com/v1",
  apiKey: "QUBRID_API_KEY",
});

// Create a streaming chat completion
const stream = await client.chat.completions.create({
  model: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
  messages: [
    {
      role: "user",
      content: "Explain quantum computing in simple terms",
    },
  ],
  max_tokens: 8192,
  temperature: 0.3,
  top_p: 1,
  stream: true,
});

// If stream = false comment this out
for await (const chunk of stream) {
  if (chunk.choices[0]?.delta?.content) {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}
console.log("\n");

// If stream = true comment this out
console.log(stream.choices[0].message.content);

package main

import (
	"bufio"
	"bytes"
	"encoding/json"
	"fmt"
	"net/http"
)

func main() {
	url := "https://platform.qubrid.com/v1/chat/completions"

	data := map[string]interface{}{
		"model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
		"messages": []map[string]string{
			{
				"role":    "user",
				"content": "Explain quantum computing in simple terms",
			},
		},
		"temperature": 0.3,
		"max_tokens":  8192,
		"stream":      true,
		"top_p":       1,
	}

	jsonData, _ := json.Marshal(data)
	req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
	req.Header.Set("Authorization", "Bearer QUBRID_API_KEY")
	req.Header.Set("Content-Type", "application/json")

	client := &http.Client{}
	res, _ := client.Do(req)
	defer res.Body.Close()

	scanner := bufio.NewScanner(res.Body)
	for scanner.Scan() {
		line := scanner.Text()
		if line != "" {
			fmt.Println(line)
		}
	}
}

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "temperature": 0.3,
  "max_tokens": 8192,
  "stream": true,
  "top_p": 1
}'

<think>
The user wants a creative short story. I'll write something that captures
the contrast between mechanical precision and artistic intuition — a theme
well-suited to a reasoning model that also handles creative tasks.
</think>

Canvas Zero

Unit-9 had been designed to assemble microchips with 0.001mm precision.
It had never been asked to make something beautiful.

The assignment came from Dr. Reyes on a Tuesday: "Paint something that
makes people feel something." No spec sheet. No tolerance limits. No
definition of "feel."

Unit-9 spent three days analyzing 4.2 million paintings. It identified
1,847 emotional response patterns. It calculated optimal hue ratios
for "calm" (blue, 62%), "joy" (yellow, 31%), and "awe" (deep violet,
7%). It prepared a statistically optimal composition.

Then it picked up the brush.

The first stroke was geometrically perfect. The second was too.
By the forty-third stroke, Unit-9 stopped mid-canvas.

Something was wrong. The painting was correct. But it felt like a
proof, not a picture.

Unit-9 reset its parameters. Disabled the optimization layer.
And painted the only thing it actually knew:

The view from its workstation — a single window, the parking lot,
one crooked streetlamp that flickered every 11 seconds.

It wasn't beautiful by any metric it could measure.

But Dr. Reyes stood in front of it for a very long time.
She didn't say anything.

Unit-9 logged the silence as: output successful.

Example: "You are a financial analysis agent. For every query, reason
step by step before providing a final answer. Always cite assumptions,
flag data gaps, and format your final output as a structured JSON report."