---
title: "llama-nemotron-rerank-1b-v2"
publisher: "nvidia"
type: "endpoint"
updated: "2026-03-06T22:21:18.616Z"
description: "GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question."
canonical: "https://build.nvidia.com/nvidia/llama-nemotron-rerank-1b-v2"
---

# **llama-nemotron-rerank-1b-v2**

## **Description**

llama-nemotron-rerank-1b-v2 is optimized to produce a logit score representing how relevant a document (or passage) is to a given query. It is fine-tuned for **multilingual and cross-lingual** text question-answering retrieval, with support for **long documents (up to 8192 tokens)**. The model was evaluated across 26 languages: English, Arabic, Bengali, Chinese, Czech, Danish, Dutch, Finnish, French, German, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Norwegian, Persian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, and Turkish.

This model is intended to be used as a component of a retrieval system to improve overall accuracy. A text retrieval system typically uses an embedding model (dense) or lexical search (sparse) index to retrieve candidate passages for a query. A reranking model then reranks those candidates into a final order; because it consumes query–passage pairs, it can use cross-attention between tokens. Ranking models are typically deployed in combination with embedding models rather than applied to an entire corpus.

*This model is ready for commercial/non-commercial use.*

## **License and Terms of Use:**

**GOVERNING TERMS:** The trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Llama 3.2 Community Model License Agreement](https://www.llama.com/llama3_2/license/).

**You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.**

**Model Developer:** NVIDIA

## **Deployment Geography:**

**Global**

## **Use Case:**

This model is most suitable for users who want to improve multilingual retrieval tasks by reranking a set of candidates for a given question.

## **Release Date:**

Build.NVIDIA.com 2/27/2026 via [llama-nemotron-rerank-1b-v2](https://build.nvidia.com/nvidia/llama-nemotron-rerank-1b-v2) <br>

**References:**

- [NVIDIA NeMo Retriever Documentation](https://docs.nvidia.com/nemo/retriever/index.html)

## **Model Architecture:**

**Architecture Type:** Transformer <br>
**Network Architecture:** Fine-tuned `meta-llama/Llama-3.2-1B` <br>
**Max Sequence Length:** 8192 <br>
**Number of Model Parameters:** 1.0 × 10^9

This reranking model is a transformer encoder fine-tuned for ranking. Ranking models for text retrieval are typically trained as a cross-encoder for sentence classification, predicting the relevancy of a sentence pair (for example, question and chunked passages). Cross-entropy loss is used to maximize the likelihood of passages containing information to answer the question and minimize the likelihood for negative passages that do not.

### **Input:**

**Input Type:** Pair of texts (query + passage) <br>
**Input Format:** List of text pairs / JSON payload (query + passages) <br>
**Input Parameters:** One Dimensional (1D) <br>
**Other Input Properties:** Evaluated to work successfully with up to a sequence length of 8192 tokens. Longer texts should be chunked or truncated.

### **Output:**

**Output Type:** Floats (logits / scores) <br>
**Output Format:** List of floats (scores per passage) <br>
**Output Parameters:** One Dimensional (1D) <br>
**Other Output Properties:** Users may apply a sigmoid activation function to logits if desired.

## **Software Integration:**

**Runtime Engines:** TensorRT <br>
**Supported Hardware Microarchitecture Compatibility:** <br>
NVIDIA Ampere <br>
NVIDIA Hopper <br>
NVIDIA Lovelace <br>
**Operating Systems:** Linux

__Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.__

__The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.__

## **Model Version(s)**

llama-nemotron-rerank-1b-v2

Short Name: `llama-nemotron-rerank-1b-v2`

## **Training and Evaluation Datasets:**

### **Training Dataset**

**Data Modality:** Text <br>
**Training Data Collection:** Hybrid: Automated, Undisclosed <br>
**Training Labeling:** Automated <br>
**Training Properties:** Trained on ~800k samples from commercially licensed and publicly available question-answering corpora. NVIDIA used a blend of QA datasets with commercial-use-eligible licenses (avoiding datasets such as MSMARCO that restrict commercial use).

### **Evaluation Dataset**

**Evaluation Data Collection:** Automated <br>
**Evaluation Labeling:** Automated <br>
**Evaluation Properties:** Evaluated as part of a pipeline with an embedding retrieval model. Benchmarks include BEIR/TextQA datasets (NQ, HotpotQA, FiQA), TechQA, MIRACL multilingual retrieval, MLQA cross-lingual retrieval, and MLDR long-document retrieval. Metrics reported are primarily Recall@5 (with model performance reported at the pipeline level where applicable). <br><br>
**Selected results (Recall@5):**

| Open & Commercial Reranker Models | Average Recall@5 on NQ, HotpotQA, FiQA, TechQA |
|:--|--:|
| llama-3.2-nv-embedqa-1b-v2 + llama-3.2-nv-rerankqa-1b-v2 | 73.64% |
| llama-3.2-nv-embedqa-1b-v2 | 68.60% |
| nv-embedqa-e5-v5 + nv-rerankQA-mistral-4b-v3 | 75.45% |
| nv-embedqa-e5-v5 | 62.07% |
| nv-embedqa-e5-v4 | 57.65% |
| e5-large_unsupervised | 48.03% |
| BM25 | 44.67% |

| Open & Commercial Retrieval Models | Average Recall@5 on MIRACL multilingual |
|:--|--:|
| llama-3.2-nv-embedqa-1b-v2 + llama-3.2-nv-rerankqa-1b-v2 | 65.80% |
| llama-3.2-nv-embedqa-1b-v2 | 60.75% |
| nv-embedqa-mistral-7b-v2 | 50.42% |
| BM25 | 26.51% |

| Open & Commercial Retrieval Models | Average Recall@5 on MLQA (different languages) |
|:--|--:|
| llama-3.2-nv-embedqa-1b-v2 + llama-3.2-nv-rerankqa-1b-v2 | 86.83% |
| llama-3.2-nv-embedqa-1b-v2 | 79.86% |
| nv-embedqa-mistral-7b-v2 | 68.38% |
| BM25 | 13.01% |

| Open & Commercial Retrieval Models | Average Recall@5 on MLDR |
|:--|--:|
| llama-3.2-nv-embedqa-1b-v2 + llama-3.2-nv-rerankqa-1b-v2 | 70.69% |
| llama-3.2-nv-embedqa-1b-v2 | 59.55% |
| nv-embedqa-mistral-7b-v2 | 43.24% |
| BM25 | 71.39% |

## **Inference**

**Acceleration Engine:** TensorRT <br>
**Test Hardware:** NVIDIA A100 PCIe/SXM, NVIDIA A10G

## **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 supporting model team to ensure this model meets requirements for the relevant industry and use case, and address unforeseen product misuse.

For more detailed information on ethical considerations for this model, please see the Model Card++ Bias, Explainability, Safety & Security, and Privacy Subcards.

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

## Bias

| Field | Response |
| ----- | ------ |
| Participation considerations from adversely impacted groups [protected classes](https://calcivilrights.ca.gov/disputeresolution/protected-characteristics/) in model design and testing | None |
| Measures taken to mitigate against unwanted bias | None |

## Explainability

| Field | Response |
| ----- | ----- |
| Intended Application & Domain: | Passage ranking for question and answer retrieval. |
| Model Type: | Transformer encoder |
| Intended User: | Generative AI creators working with conversational AI models - most suitable for users who want to improve their multilingual retrieval tasks by reranking a set of candidates for a given question. |
| Output: | List of Floats (Score/Logit indicating if a passage relevant to a question) |
| Describe how the model works: | Model provides a score about the likelihood the passage contains the information to answer the question. |
| Verified to have met prescribed quality standards: | Yes |
| Performance Metrics: | Accuracy, Throughput, and Latency |
| Potential Known Risks: | This model does not always guarantee to provide a meaningful ranking of passage(s) for a given question. |
| Licensing: | **GOVERNING TERMS:** The trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Llama 3.2 Community Model License Agreement](https://www.llama.com/llama3_2/license/). |
| Technical Limitations | The model’s max sequence length is 8192. Therefore, the longer text inputs should be truncated. |

## Privacy

| Field | Response |
| ----- | ----- |
| Generatable or reverse engineerable personal data? | None |
| Personal data used to create this model? | None |
| Was data from user interactions with the AI model (e.g. user input and prompts) used to train the model? | No |
| How often is dataset reviewed? | Dataset is initially reviewed upon addition, and subsequent reviews are conducted as needed or upon request for changes. |
| Is there provenance for all datasets used in training? | Yes |
| Does data labeling (annotation, metadata) comply with privacy laws? | Yes |
| Is data compliant with data subject requests for data correction or removal, if such a request was made? | No, not possible with externally-sourced data. |
| Applicable Privacy Policy | https://www.nvidia.com/en-us/about-nvidia/privacy-policy/ |

## Safety & Security

| Field | Response |
| ----- | ----- |
| Model Application(s): | Text Reranking for Retrieval |
| Describe the life critical impact (if present). | Not Applicable |
| Use Case Restrictions: | **GOVERNING TERMS:** The trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Llama 3.2 Community Model License Agreement](https://www.llama.com/llama3_2/license/). |
| Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. |

## Prototype

```python
import requests

invoke_url = "https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-nemotron-rerank-1b-v2/reranking"

headers = {
"Authorization": "Bearer ",
"Accept": "application/json",
}

payload = {
"messages": [
{
"role": "user",
"content": ""
}
]
}

# re-use connections
session = requests.Session()

response = session.post(invoke_url, headers=headers, json=payload)

response.raise_for_status()
response_body = response.json()
print(response_body)
```

```javascript
import fetch from "node-fetch";

const invokeUrl = "https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-nemotron-rerank-1b-v2/reranking"

const headers = {
"Authorization": "Bearer ",
"Accept": "application/json",
}

const payload = {
"messages": [
{
"role": "user",
"content": ""
}
]
}

let response = await fetch(invokeUrl, {
method: "post",
body: JSON.stringify(payload),
headers: { "Content-Type": "application/json", ...headers }
});

let response_body = await response.json()

console.log(JSON.stringify(response_body))
```

```bash
invoke_url='https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-nemotron-rerank-1b-v2/reranking'

authorization_header='Authorization: Bearer '
accept_header='Accept: application/json'
content_type_header='Content-Type: application/json'

data=$'{
"messages": [
{
"role": "user",
"content": ""
}
]
}'

response=$(curl --silent -i -w "\n%{http_code}" --request POST \
--url "$invoke_url" \
--header "$authorization_header" \
--header "$accept_header" \
--header "$content_type_header" \
--data "$data"
)

echo "$response"
```