Llama 3.1 Nemotron Nano 8B V1 GGUF

🚀 Llama-3.1-Nemotron-Nano-8B-v1

Llama-3.1-Nemotron-Nano-8B-v1 is a large language model offering a great balance between accuracy and efficiency, suitable for various AI applications.

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

📋 Model Information

✨ Features

• Great Tradeoff: Offers a great balance between model accuracy and efficiency.
• Local Usability: Fits on a single RTX GPU and can be used locally.
• Long Context Support: Supports a context length of 128K.
• Multi - phase Training: Underwent a multi - phase post - training process to enhance reasoning and non - reasoning capabilities.
• Commercial Use: Ready for commercial use.

🚀 Quick Start

Usage Recommendations

1. Reasoning Mode Control: The reasoning mode (ON/OFF) is controlled via the system prompt, which must be set as shown in the examples below. All instructions should be contained within the user prompt.
2. Parameter Settings:
   • Reasoning ON: Set temperature to 0.6, and Top P to 0.95.
   • Reasoning OFF: Use greedy decoding.
3. Evaluation Prompts: A list of prompts for evaluation is provided for each benchmark where a specific template is required.
4. Expected Behavior: In Reasoning ON mode, the model will include <think></think> if no reasoning was necessary.

You can try this model out through the preview API, using this link: Llama-3.1-Nemotron-Nano-8B-v1.

💻 Usage Examples

Basic Usage

import torch
import transformers

model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1"
model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"}
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
tokenizer.pad_token_id = tokenizer.eos_token_id

pipeline = transformers.pipeline(
   "text-generation",
   model=model_id,
   tokenizer=tokenizer,
   max_new_tokens=32768,
   temperature=0.6,
   top_p=0.95,
   **model_kwargs
)

# Thinking can be "on" or "off"
thinking = "on"

print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x*(sin(x)+2)=0"}]))

Advanced Usage

Reasoning Off Mode

import torch
import transformers

model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1"
model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"}
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
tokenizer.pad_token_id = tokenizer.eos_token_id

# Thinking can be "on" or "off"
thinking = "off"

pipeline = transformers.pipeline(
   "text-generation",
   model=model_id,
   tokenizer=tokenizer,
   max_new_tokens=32768,
   do_sample=False,
   **model_kwargs
)

print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x*(sin(x)+2)=0"}]))

Preventing Unwanted Thinking

import torch
import transformers

model_id = "nvidia/Llama-3.1-Nemotron-Nano-8B-v1"
model_kwargs = {"torch_dtype": torch.bfloat16, "device_map": "auto"}
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
tokenizer.pad_token_id = tokenizer.eos_token_id

# Thinking can be "on" or "off"
thinking = "off"

pipeline = transformers.pipeline(
   "text-generation",
   model=model_id,
   tokenizer=tokenizer,
   max_new_tokens=32768,
   do_sample=False,
   **model_kwargs
)

print(pipeline([{"role": "system", "content": f"detailed thinking {thinking}"}, {"role": "user", "content": "Solve x*(sin(x)+2)=0"}, {"role":"assistant", "content":"<think>\n</think>"}]))

📚 Documentation

Model Overview

Llama-3.1-Nemotron-Nano-8B-v1 is a large language model (LLM) which is a derivative of Meta Llama-3.1-8B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling.

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 REINFORCE (RLOO) and Online Reward - aware Preference Optimization (RPO) algorithms for both chat and instruction - following. The final model checkpoint is obtained after merging the final SFT and Online RPO checkpoints. Improved using Qwen.

This model is part of the Llama Nemotron Collection. You can find the other model(s) in this family here: Llama-3.3-Nemotron-Super-49B-v1.

License/Terms of Use

GOVERNING TERMS: Your use of this model is governed by the NVIDIA Open Model License. Additional Information: Llama 3.1 Community License Agreement. Built with Llama.

Model Developer: NVIDIA

Model Dates: Trained between August 2024 and March 2025

Data Freshness: The pretraining data has a cutoff of 2023 per Meta Llama 3.1 8B

Use Case

Suitable for developers designing AI Agent systems, chatbots, RAG systems, and other AI - powered applications. Also suitable for typical instruction - following tasks. Balances model accuracy and compute efficiency.

Release Date

3/18/2025

References

• [2505.00949] Llama-Nemotron: Efficient Reasoning Models
• [2502.00203] Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment

Model Architecture

• Architecture Type: Dense decoder - only Transformer model
• Network Architecture: Llama 3.1 8B Instruct

Intended Use

Llama-3.1-Nemotron-Nano-8B-v1 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

Model Version

1.0 (3/18/2025)

Software Integration

• Runtime Engine: NeMo 24.12
• Recommended Hardware Microarchitecture Compatibility:
  • NVIDIA Hopper
  • NVIDIA Ampere

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
• 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-8B-v1.

• 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.

⚠️ Important 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

MATH500

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

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

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{}"

IFEval Average

BFCL v2 Live

User Prompt Template:

<AVAILABLE_TOOLS>{functions}</AVAILABLE_TOOLS>

{user_prompt}

MBPP 0 - shot

User Prompt Template:

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

## 🔧 Technical Details
### 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.

For more detailed information on ethical considerations for this model, please see the Model Card++ [Explainability](explainability.md), [Bias](bias.md), [Safety & Security](safety.md), and [Privacy](privacy.md) Subcards.

Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

### Citation

@misc{bercovich2025llamanemotronefficientreasoningmode

## 📄 License
Your use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/).