---
title: Qwen2.5-Coder-0.5B-4bit-gs32
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32.md"
repository: mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32
last_updated: 2025-01-14
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Qwen/Qwen2.5-Coder-0.5B
base_model_relation: quantized
parameters: 92.7M
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 2627
stars: 0
tags:
  - code
  - qwen
  - qwen-coder
  - codeqwen
  - mlx
---

# Qwen2.5-Coder-0.5B-4bit-gs32

> Qwen2.5-Coder-0.5B-4bit-gs32 - mlx-community 在 ModelScope 开源的模型。mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32

mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32 是 ModelScope 魔搭社区上的 92.7M 参数text-generation模型，采用 apache-2.0 许可，基于 Qwen/Qwen2.5-Coder-0.5B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 92.7M
- **Base model**: Qwen/Qwen2.5-Coder-0.5B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: code, qwen, qwen-coder, codeqwen, mlx
- **Downloads**: 2627
- **Stars**: 0
- **Last updated**: 2025-01-14

Source: https://www.modelscope.cn/models/mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32

---

# mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32

The Model [mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32](https://huggingface.co/mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32) was
converted to MLX format from [Qwen/Qwen2.5-Coder-0.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B)
using mlx-lm version **0.21.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-0.5B-4bit-gs32")

prompt = "hello"

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

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