---
title: DeepSeek-R1
canonical_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-R1"
md_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-R1.md"
repository: mlx-community/DeepSeek-R1
last_updated: 2025-05-07
license: mit
model_type:
  - deepseek_v3
architectures:
  - DeepseekV3ForCausalLM
base_model:
  - deepseek-ai/DeepSeek-R1
base_model_relation: quantized
library_name:
  - mlx
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 362
stars: 0
---

# DeepSeek-R1

> DeepSeek-R1 - mlx-community 在 ModelScope 开源的模型。mlx-community/DeepSeek-R1

mlx-community/DeepSeek-R1 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可，基于 deepseek-ai/DeepSeek-R1 构建，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/DeepSeek-R1
- **License**: mit
- **Base model**: deepseek-ai/DeepSeek-R1
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 362
- **Stars**: 0
- **Last updated**: 2025-05-07

Source: https://www.modelscope.cn/models/mlx-community/DeepSeek-R1

---

# mlx-community/DeepSeek-R1

The Model [mlx-community/DeepSeek-R1](https://huggingface.co/mlx-community/DeepSeek-R1) was
converted to MLX format from [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)
using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-R1")

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)
```