---
title: DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit.md"
repository: mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit
last_updated: 2025-02-27
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
base_model_relation: quantized
parameters: 5.1B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 996
stars: 1
tags:
  - mlx
---

# DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit

> DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit - mlx-community 在 ModelScope 开源的模型。mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX

mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit 是 ModelScope 魔搭社区上的 5.1B 参数机器学习模型，基于 deepseek-ai/DeepSeek-R1-Distill-Qwen-32B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit
- **Parameters**: 5.1B
- **Base model**: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 996
- **Stars**: 1
- **Last updated**: 2025-02-27

Source: https://www.modelscope.cn/models/mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX-4Bit

---

# mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX

The Model [mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX](https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX) was
converted to MLX format from [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B)
using mlx-lm version **0.21.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-R1-Distill-Qwen-32B-MLX")

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)
```