Instructions to use nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1")
model = AutoModelForCausalLM.from_pretrained("nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1

SGLang

How to use nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 with Docker Model Runner:
```
docker model run hf.co/nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1
```

Adding system block with "detailed thinking off" even when system role not present in messages

by ameyasunilm - opened Jun 4, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-3

Files changed (1) hide show

llama_nemotron_nano_generic_tool_calling.jinja +9 -3

llama_nemotron_nano_generic_tool_calling.jinja CHANGED Viewed

@@ -1,7 +1,9 @@
 {%- if tools %}
     {{- '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n' -}}
-    {%- if messages[0].role == 'system' -%}
         {{- messages[0].content + '\n\n' -}}
     {%- endif -%}
     {{- '<AVAILABLE_TOOLS>[' -}}
     {%- for tool in tools -%}
@@ -9,9 +11,13 @@
     {%- endfor -%}
     {{- ']</AVAILABLE_TOOLS>' -}}{{- '<|eot_id|>' -}}
 {%- else %}
-    {%- if messages[0].role == 'system' %}
-        {{- '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n' + messages[0].content + '<|eot_id|>' -}}
     {%- endif %}
 {%- endif %}
 {%- for message in messages -%}
     {%- if (message.role == 'user') -%}

 {%- if tools %}
     {{- '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n' -}}
+    {%- if messages[0].role == 'system' and messages[0].content != '' -%}
         {{- messages[0].content + '\n\n' -}}
+    {%- else -%}
+        {{- 'detailed thinking off\n\n' -}}
     {%- endif -%}
     {{- '<AVAILABLE_TOOLS>[' -}}
     {%- for tool in tools -%}
     {%- endfor -%}
     {{- ']</AVAILABLE_TOOLS>' -}}{{- '<|eot_id|>' -}}
 {%- else %}
+    {{- '<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n' -}}
+    {%- if messages[0].role == 'system' and messages[0].content != '' -%}
+        {{- messages[0].content -}}
+    {%- else -%}
+        {{- 'detailed thinking off' -}}
     {%- endif %}
+    {{- '<|eot_id|>' -}}
 {%- endif %}
 {%- for message in messages -%}
     {%- if (message.role == 'user') -%}