---
title: Index-Translate-9B-MLX-mxfp8
canonical_url: "https://www.modelscope.cn/models/mlx-community/Index-Translate-9B-MLX-mxfp8"
md_url: "https://www.modelscope.cn/models/mlx-community/Index-Translate-9B-MLX-mxfp8.md"
repository: mlx-community/Index-Translate-9B-MLX-mxfp8
last_updated: 2026-10-29
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - IndexTeam/Index-Translate-9B
base_model_relation: quantized
parameters: 2.5B
tensor_type:
  - U8
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 6
stars: 0
tags:
  - translation
  - index
  - mlx
---

# Index-Translate-9B-MLX-mxfp8

> Index-Translate-9B-MLX-mxfp8 - mlx-community 在 ModelScope 开源的模型。mlx-community/Index-Translate-9B-MLX-mxfp8

mlx-community/Index-Translate-9B-MLX-mxfp8 是 ModelScope 魔搭社区上的 2.5B 参数text-generation模型，采用 apache-2.0 许可，基于 IndexTeam/Index-Translate-9B 构建。

- **Repository**: mlx-community/Index-Translate-9B-MLX-mxfp8
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 2.5B
- **Base model**: IndexTeam/Index-Translate-9B
- **Tags**: translation, index, mlx
- **Downloads**: 6
- **Stars**: 0
- **Last updated**: 2026-10-29

Source: https://www.modelscope.cn/models/mlx-community/Index-Translate-9B-MLX-mxfp8

---

# mlx-community/Index-Translate-9B-MLX-mxfp8

This model [mlx-community/Index-Translate-9B-MLX-mxfp8](https://huggingface.co/mlx-community/Index-Translate-9B-MLX-mxfp8) was
converted to MLX format from [IndexTeam/Index-Translate-9B](https://huggingface.co/IndexTeam/Index-Translate-9B)
using mlx-lm version **0.32.2**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Index-Translate-9B-MLX-mxfp8")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```