---
title: Qwen3-Reranker-8B-mxfp8
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen3-Reranker-8B-mxfp8"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen3-Reranker-8B-mxfp8.md"
repository: mlx-community/Qwen3-Reranker-8B-mxfp8
last_updated: 2026-02-16
license: apache-2.0
pipeline_tag: text-ranking
tasks:
  - text-ranking
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - Qwen/Qwen3-8B-Base
base_model_relation: finetune
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 395
stars: 1
tags:
  - mlx
---

# Qwen3-Reranker-8B-mxfp8

> Qwen3-Reranker-8B-mxfp8 - mlx-community 在 ModelScope 开源的模型。mlx-community/Qwen3-Reranker-8B-mxfp8

mlx-community/Qwen3-Reranker-8B-mxfp8 是 ModelScope 魔搭社区上的text-ranking模型，采用 apache-2.0 许可，基于 Qwen/Qwen3-8B-Base 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/Qwen3-Reranker-8B-mxfp8
- **License**: apache-2.0
- **Tasks**: text-ranking
- **Base model**: Qwen/Qwen3-8B-Base
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 395
- **Stars**: 1
- **Last updated**: 2026-02-16

Source: https://www.modelscope.cn/models/mlx-community/Qwen3-Reranker-8B-mxfp8

---

# mlx-community/Qwen3-Reranker-8B-mxfp8

The Model [mlx-community/Qwen3-Reranker-8B-mxfp8](https://huggingface.co/mlx-community/Qwen3-Reranker-8B-mxfp8) was converted to MLX format from [Qwen/Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) using [mlx-embeddings](https://github.com/Blaizzy/mlx-embeddings) version **0.0.3**.

## Use with mlx

```bash
pip install mlx-embeddings
```

```python
from mlx_embeddings import load, generate
import mlx.core as mx

model, tokenizer = load("mlx-community/Qwen3-Reranker-8B-mxfp8")

# For text embeddings
output = generate(model, processor, texts=["I like grapes", "I like fruits"])
embeddings = output.text_embeds  # Normalized embeddings

# Compute dot product between normalized embeddings
similarity_matrix = mx.matmul(embeddings, embeddings.T)

print("Similarity matrix between texts:")
print(similarity_matrix)


```