---
license: mit
---

## Overview

**DeepSeek** developed and released the [DeepSeek R1 Distill Qwen 7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) model, a distilled version of the Qwen 7B language model. This version is fine-tuned for high-performance text generation and optimized for dialogue and information-seeking tasks, providing even greater capabilities with its larger size compared to the 7B variant.

The model is designed for applications in customer support, conversational AI, and research, focusing on delivering accurate, helpful, and safe outputs while maintaining efficiency.

## Variants

| No | Variant | Cortex CLI command |
| --- | --- | --- |
| 1 | [gguf](https://huggingface.co/cortexso/deepseek-r1-distill-qwen-7b/tree/main) | `cortex run deepseek-r1-distill-qwen-7b` |

## Use it with Jan (UI)

1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
2. Use in Jan model Hub:
    ```text
    cortexso/deepseek-r1-distill-qwen-7b
    ```

## Use it with Cortex (CLI)

1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
2. Run the model with command:
    ```bash
    cortex run deepseek-r1-distill-qwen-7b
    ```

## Credits

- **Author:** DeepSeek
- **Converter:** [Homebrew](https://www.homebrew.ltd/)
- **Original License:** [License](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B#7-license)
- **Papers:** [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://arxiv.org/html/2501.12948v1)