Qwen3-Reranker-0.6B

Qwen3-Reranker-0.6B

This repository contains Qwen/Qwen3-Reranker-0.6B together with a Furiosa Executable Bundle (FXB) for running it on FuriosaAI RNGD with Furiosa-LLM. The same model also runs on other frameworks (such as Sentence Transformers, vLLM, and Transformers); for usage with those, see the upstream Qwen/Qwen3-Reranker-0.6B model card.

Overview

Qwen3-Reranker-0.6B is the 0.6B reranking model in the Qwen3-Reranker series, built on the Qwen3 dense transformer backbone. Given a query and a set of candidate documents, it produces relevance scores used to reorder retrieval results — a common second stage in retrieval-augmented generation (RAG) and search pipelines. Its intended use is the same as the upstream Qwen/Qwen3-Reranker-0.6B, and it is released under the Apache 2.0 License.

• Architecture: Qwen3 (dense)
• Input / Output: Text (query-document pairs) / Relevance score
• Supported Inference Engine: Furiosa LLM
• Supported Hardware: FuriosaAI RNGD

Quantization

No quantization — the model runs in its native BF16 precision.

Parallelism Strategy

On RNGD, Qwen3-Reranker-0.6B runs with a tensor-parallel size of 8 PEs, which maps to a single RNGD card (8 PEs per card).

Usage

To run this model with Furiosa-LLM, follow the examples below after installing Furiosa-LLM and its prerequisites. You can use the model either online through the OpenAI-compatible server or offline through the Furiosa-LLM Python API.

Launch the server

The simplest way to serve the model is:

# Launch the server, listening on port 8000 by default
furiosa-llm serve furiosa-ai/Qwen3-Reranker-0.6B

When the server is ready, you will see:

INFO:     Started server process [27507]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

Basic Usage

The server exposes a /v1/rerank endpoint (compatible with the Cohere/Jina rerank API, also used by vLLM). Send a query and the candidate documents with curl; the server returns the documents reordered by relevance_score:

curl http://localhost:8000/v1/rerank \
    -H "Content-Type: application/json" \
    -d '{
    "model": "furiosa-ai/Qwen3-Reranker-0.6B",
    "query": "What is deep learning?",
    "documents": [
        "Deep learning is a subset of machine learning using neural networks.",
        "Python is a popular programming language for data science.",
        "Neural networks are inspired by biological neural networks."
    ]
    }' \
    | python -m json.tool

You can do the same from Python with the requests library, and pass top_n to keep only the most relevant documents:

import requests

response = requests.post(
    "http://localhost:8000/v1/rerank",
    json={
        "model": "furiosa-ai/Qwen3-Reranker-0.6B",
        "query": "What is deep learning?",
        "documents": [
            "Deep learning is a subset of machine learning using neural networks.",
            "Python is a popular programming language for data science.",
            "Neural networks are inspired by biological neural networks.",
        ],
        "top_n": 2,
    },
)

for result in response.json()["results"]:
    print(f"score={result['relevance_score']:.4f}  {result['document']['text']}")

To score query-document pairs directly instead of reranking, the server also exposes a /v1/score endpoint.

Advanced Usage

For offline use, load the model with the LLM constructor (the FXB shipped in the repo is discovered automatically) and call score with a query and the candidate documents to obtain relevance scores:

from furiosa_llm import LLM

with LLM("furiosa-ai/Qwen3-Reranker-0.6B") as llm:
    query = "What is deep learning?"
    documents = [
        "Deep learning is a subset of machine learning using neural networks.",
        "Python is a popular programming language for data science.",
    ]
    outputs = llm.score(query, documents)
    for document, output in zip(documents, outputs):
        print(f"score={output.outputs.score:.4f}  {document}")

Learn more

• Furiosa-LLM Server (furiosa-llm serve) — full OpenAI-compatible API reference, including the Rerank and Score APIs
• Furiosa-LLM — Furiosa-LLM documentation and API reference
• Qwen/Qwen3-Reranker-0.6B — upstream model card