Llama-3.1-Nemotron-Nano-4B-v1.1 is a large language model (LLM) which is a derivative of nvidia/Llama-3.1-Minitron-4B-Width-Base, which is created from Llama 3.1 8B using our LLM compression technique and offers improvements in model accuracy and efficiency. It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling.
Llama-3.1-Nemotron-Nano-4B-v1.1 is a model which offers a great tradeoff between model accuracy and efficiency. The model fits on a single RTX GPU and can be used locally. The model supports a context length of 128K.
This model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Reasoning, and Tool Calling as well as multiple reinforcement learning (RL) stages using Reward-aware Preference Optimization (RPO) algorithms for both chat and instruction-following. The final model checkpoint is obtained after merging the final SFT and RPO checkpoints
This model is part of the Llama Nemotron Collection. You can find the other model(s) in this family here:
Model Dates: Trained between August 2024 and May 2025
Data Freshness: The pretraining data has a cutoff of June 2023.
Use Case:
Developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. Also suitable for typical instruction-following tasks. Balance of model accuracy and compute efficiency (the model fits on a single RTX GPU and can be used locally).
Architecture Type: Dense decoder-only Transformer model
Network Architecture: Llama 3.1 Minitron Width 4B Base
Intended use
Llama-3.1-Nemotron-Nano-4B-v1.1 is a general purpose reasoning and chat model intended to be used in English and coding languages. Other non-English languages (German, French, Italian, Portuguese, Hindi, Spanish, and Thai) are also supported.
Input:
Input Type: Text
Input Format: String
Input Parameters: One-Dimensional (1D)
Other Properties Related to Input: Context length up to 131,072 tokens
Output:
Output Type: Text
Output Format: String
Output Parameters: One-Dimensional (1D)
Other Properties Related to Output: Context length up to 131,072 tokens
Reasoning mode (ON/OFF) is controlled via the system prompt, which must be set as shown in the example below. All instructions should be contained within the user prompt
We recommend setting temperature to 0.6, and Top P to 0.95 for Reasoning ON mode
We recommend using greedy decoding for Reasoning OFF mode
We have provided a list of prompts to use for evaluation for each benchmark where a specific template is required
See the snippet below for usage with Hugging Face Transformers library. Reasoning mode (ON/OFF) is controlled via system prompt. Please see the example below.
Our code requires the transformers package version to be 4.44.2 or higher.
1import torch
2import transformers
34model_id ="nvidia/Llama-3.1-Nemotron-Nano-4B-v1"5model_kwargs ={"torch_dtype": torch.bfloat16,"device_map":"auto"}6tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)7tokenizer.pad_token_id = tokenizer.eos_token_id
89pipeline = transformers.pipeline(10"text-generation",11 model=model_id,12 tokenizer=tokenizer,13 max_new_tokens=32768,14 do_sample=False,15**model_kwargs
16)1718# Thinking can be "on" or "off"19thinking ="off"2021print(pipeline([{"role":"system","content":f"detailed thinking {thinking}"},{"role":"user","content":"Solve x*(sin(x)+2)=0"}]))
For some prompts, even though thinking is disabled, the model emergently prefers to think before responding. But if desired, the users can prevent it by pre-filling the assistant response.
python
1import torch
2import transformers
34model_id ="nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1"5model_kwargs ={"torch_dtype": torch.bfloat16,"device_map":"auto"}6tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)7tokenizer.pad_token_id = tokenizer.eos_token_id
89# Thinking can be "on" or "off"10thinking ="off"1112pipeline = transformers.pipeline(13"text-generation",14 model=model_id,15 tokenizer=tokenizer,16 max_new_tokens=32768,17 do_sample=False,18**model_kwargs
19)2021print(pipeline([{"role":"system","content":f"detailed thinking {thinking}"},{"role":"user","content":"Solve x*(sin(x)+2)=0"},{"role":"assistant","content":"<think>\n</think>"}]))
Running a vLLM Server with Tool-call Support
Llama-3.1-Nemotron-Nano-4B-v1.1 supports tool calling. This HF repo hosts a tool-callilng parser as well as a chat template in Jinja, which can be used to launch a vLLM server.
Here is a shell script example to launch a vLLM server with tool-call support. vllm/vllm-openai:v0.6.6 or newer should support the model.
After launching a vLLM server, you can call the server with tool-call support using a Python script like below.
python
1>>>from openai import OpenAI
2>>> client = OpenAI(3 base_url="http://0.0.0.0:5000/v1",4 api_key="dummy",5)67>>> completion = client.chat.completions.create(8 model="Llama-Nemotron-Nano-4B-v1.1",9 messages=[10{"role":"system","content":"detailed thinking on"},11{"role":"user","content":"My bill is $100. What will be the amount for 18% tip?"},12],13 tools=[14{"type":"function","function":{"name":"calculate_tip","parameters":{"type":"object","properties":{"bill_total":{"type":"integer","description":"The total amount of the bill"},"tip_percentage":{"type":"integer","description":"The percentage of tip to be applied"}},"required":["bill_total","tip_percentage"]}}},15{"type":"function","function":{"name":"convert_currency","parameters":{"type":"object","properties":{"amount":{"type":"integer","description":"The amount to be converted"},"from_currency":{"type":"string","description":"The currency code to convert from"},"to_currency":{"type":"string","description":"The currency code to convert to"}},"required":["from_currency","amount","to_currency"]}}},16],17)1819>>> completion.choices[0].message.content
20'<think>\nOkay, let\'s see. The user has a bill of $100 and wants to know the amount of a 18% tip. So, I need to calculate the tip amount. The available tools include calculate_tip, which requires bill_total and tip_percentage. The parameters are both integers. The bill_total is 100, and the tip percentage is 18. So, the function should multiply 100 by 18% and return 18.0. But wait, maybe the user wants the total including the tip? The question says "the amount for 18% tip," which could be interpreted as the tip amount itself. Since the function is called calculate_tip, it\'s likely that it\'s designed to compute the tip, not the total. So, using calculate_tip with bill_total=100 and tip_percentage=18 should give the correct result. The other function, convert_currency, isn\'t relevant here. So, I should call calculate_tip with those values.\n</think>\n\n'2122>>> completion.choices[0].message.tool_calls
23[ChatCompletionMessageToolCall(id='chatcmpl-tool-2972d86817344edc9c1e0f9cd398e999', function=Function(arguments='{"bill_total": 100, "tip_percentage": 18}', name='calculate_tip'),type='function')]
Inference:
Engine: Transformers
Test Hardware:
BF16:
1x RTX 50 Series GPUs
1x RTX 40 Series GPUs
1x RTX 30 Series GPUs
1x H100-80GB GPU
1x A100-80GB GPU
Jetson AGX Thor
Preferred/Supported] Operating System(s): Linux
Training Datasets
A large variety of training data was used for the post-training pipeline, including manually annotated data and synthetic data.
The data for the multi-stage post-training phases for improvements in Code, Math, and Reasoning is a compilation of SFT and RL data that supports improvements of math, code, general reasoning, and instruction following capabilities of the original Llama instruct model.
Prompts have been sourced from either public and open corpus or synthetically generated. Responses were synthetically generated by a variety of models, with some prompts containing responses for both Reasoning On and Off modes, to train the model to distinguish between two modes.
Data Collection for Training Datasets:
Hybrid: Automated, Human, Synthetic
Data Labeling for Training Datasets:
N/A
Evaluation Datasets
We used the datasets listed below to evaluate Llama-3.1-Nemotron-Nano-4B-v1.1.
Data Collection for Evaluation Datasets: Hybrid: Human/Synthetic
Data Labeling for Evaluation Datasets: Hybrid: Human/Synthetic/Automatic
Evaluation Results
These results contain both “Reasoning On”, and “Reasoning Off”. We recommend using temperature=0.6, top_p=0.95 for “Reasoning On” mode, and greedy decoding for “Reasoning Off” mode. All evaluations are done with 32k sequence length. We run the benchmarks up to 16 times and average the scores to be more accurate.
NOTE: Where applicable, a Prompt Template will be provided. While completing benchmarks, please ensure that you are parsing for the correct output format as per the provided prompt in order to reproduce the benchmarks seen below.
MT-Bench
Reasoning Mode
Score
Reasoning Off
7.4
Reasoning On
8.0
MATH500
Reasoning Mode
pass@1
Reasoning Off
71.8%
Reasoning On
96.2%
User Prompt Template:
"Below is a math question. I want you to reason through the steps and then give a final answer. Your final answer should be in \boxed{}.\nQuestion: {question}"
AIME25
Reasoning Mode
pass@1
Reasoning Off
13.3%
Reasoning On
46.3%
User Prompt Template:
"Below is a math question. I want you to reason through the steps and then give a final answer. Your final answer should be in \boxed{}.\nQuestion: {question}"
GPQA-D
Reasoning Mode
pass@1
Reasoning Off
33.8%
Reasoning On
55.1%
User Prompt Template:
"What is the correct answer to this question: {question}\nChoices:\nA. {option_A}\nB. {option_B}\nC. {option_C}\nD. {option_D}\nLet's think step by step, and put the final answer (should be a single letter A, B, C, or D) into a \boxed{}"
You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
@@ Instruction
Here is the given problem and test examples:
{prompt}
Please use the python programming language to solve this problem.
Please make sure that your code includes the functions from the test samples and that the input and output formats of these functions match the test samples.
Please return all completed codes in one code block.
This code block should be in the following format:
```python
# Your codes here
```
Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
