Please rotate your device

To continue exploring this website, please rotate your device to a vertical orientation

Llama 3.3 Nemotron 49B Super - NVIDIA NIM

NVIDIA/Llama 3.3 Nemotron 49B Super - NVIDIA NIM

A high-efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.

large language

Llama 3.3 Nemotron 49B Super is an NVIDIA NIM large language model (LLM) derived from Llama 3.3 70B Instruct. It can be deployed with early access on Baseten.

Llama 3.3 Nemotron is a reasoning model post-trained for enterprise AI agent use cases, including reasoning, tool calling, chat, and instruction following tasks with a 128k token context length.

Input

python
import requests

# Replace the empty string with your model id below
model_id = ""
baseten_api_key = os.environ["BASETEN_API_KEY"]

messages = [
    {"role": "user", "content": "Write a limerick about the wonders of GPU computing.?"},
]
data = {
    "messages": messages,
    "stream": True,
    "max_new_tokens": 512
}

# Call model endpoint
res = requests.post(
    f"https://model-{model_id}.api.baseten.co/production/predict",
    headers={"Authorization": f"Api-Key {baseten_api_key}"},
    json=data,
    stream=True
)

# Print the generated tokens as they get streamed
for content in res.iter_content():
    print(content.decode("utf-8"), end="", flush=True)

Related models

See all models