---
title: A.X-4.0-Light-MLX-BF16
canonical_url: "https://www.modelscope.cn/models/mlx-community/A.X-4.0-Light-MLX-BF16"
md_url: "https://www.modelscope.cn/models/mlx-community/A.X-4.0-Light-MLX-BF16.md"
repository: mlx-community/A.X-4.0-Light-MLX-BF16
last_updated: 2026-01-21
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
  - text2text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Qwen/Qwen2.5-7B
base_model_relation: finetune
parameters: 7.3B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ko
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 25
stars: 0
---

# A.X-4.0-Light-MLX-BF16

> A.X-4.0-Light-MLX-BF16 - mlx-community 在 ModelScope 开源的模型。[!IMPORTANT] Original Model Link : https://huggingface.co/skt/A.X-4.0-Light

mlx-community/A.X-4.0-Light-MLX-BF16 是 ModelScope 魔搭社区上的 7.3B 参数text-generation、text2text-generation模型，采用 apache-2.0 许可，基于 Qwen/Qwen2.5-7B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/A.X-4.0-Light-MLX-BF16
- **License**: apache-2.0
- **Tasks**: text-generation, text2text-generation
- **Parameters**: 7.3B
- **Base model**: Qwen/Qwen2.5-7B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 25
- **Stars**: 0
- **Last updated**: 2026-01-21

Source: https://www.modelscope.cn/models/mlx-community/A.X-4.0-Light-MLX-BF16

---

> [!IMPORTANT]
> Original Model Link : [https://huggingface.co/skt/A.X-4.0-Light](https://huggingface.co/skt/A.X-4.0-Light)
> 

```
name: A.X-4.0-Light-MLX
base_model: Qwen/Qwen2.5-7B
license: apache-2.0
pipeline_tag: text-generation
tasks :
 - text-generation
 - text2text-generation
language :
 - en
 - ko
license_link: https://huggingface.co/skt/A.X-4.0-Light/blob/main/LICENSE
get_started_code: uvx --from mlx-lm mlx_lm.generate --model  --model mlx-community/A.X-4.0-Light-MLX --prompt 'Test Prompt' --prompt 'Test prompt'
```


# A.X-4.0-Light-MLX
A.X-4.0-Light-MLX is a 7B model based on Qwen2.5

> [!WARNING]
> MLX is a framework for METAL graphics supported by Apple computers with ARM M-series processors (M1/M2/M3/M4/M5)

> [!NOTE]
> Generation using uv https://docs.astral.sh/uv/**:
> ```
> uvx --from mlx-lm mlx_lm.generate --model  --model mlx-community/A.X-4.0-Light-MLX --prompt 'Test Prompt'
>```

> [!NOTE]
> Generation using pip:
> ```
> pipx --from mlx-lm mlx_lm.generate --model  --model mlx-community/A.X-4.0-Light-MLX --prompt 'Test Prompt'
> ```