Skip to content
This page is not translated yet — showing the original. We never ship machine translation as a placeholder.
Needs a toolchainMIT Tested

DeepSeek-R1-Distill-Qwen-7B

In one line:DeepSeek-R1-Distill-Qwen-7B 是一个把推理能力蒸馏到 7B 的模型,回答前先输出思考过程。

把"先想再答"的能力压进 7B,本地也能做推理题。

Official source

We host and mirror nothing — the official page is the source of truth.

Official icon for DeepSeek-R1-Distill-Qwen-7B DeepSeek(深度求索)https://github.com/deepseek-ai/DeepSeek-R1Open official page
Official sourceYou are leaving AIWorksWell for DeepSeek(深度求索). That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.

Install prompt

Copy it, paste it into your AI (Claude Code, Codex, ChatGPT…), and it installs and verifies for you.

43 lines
我需要你帮我在我的机器上安装并运行一个软件。

【软件信息】
名称:DeepSeek-R1-Distill-Qwen-7B
用途:把"先想再答"的能力压进 7B,本地也能做推理题。
官方来源:https://github.com/deepseek-ai/DeepSeek-R1
许可:MIT
Scroll inside the box with your mouse wheel — copying still gives you the full prompt1212 chars

Copy → paste into your own AI → it installs for you

Contact the original author (DeepSeek(深度求索))

Bugs in the software itself go to the author's own official channel — that is where they actually receive them. We pass things on; we do not answer for the author.

Install failed?

Paste the raw error — once triaged and verified it is written back here, so the next person's AI avoids it. No login needed.

About this entry

它是什么

DeepSeek-R1-Distill-Qwen-7B 是把大模型推理能力蒸馏到 7B 的代表作:回答前会先输出一段思考过程,做数学与逻辑题时比同尺寸普通模型稳。来源:https://github.com/deepseek-ai/DeepSeek-R1https://github.com/deepseek-ai/DeepSeek-R1

怎么用起来

DeepSeek-R1-Distill-Qwen-7B 用与其它 7B 模型相同的本地流程跑。注意蒸馏版会输出较长的思考内容,实际速度感受会比同尺寸普通模型慢。来源:https://github.com/deepseek-ai/DeepSeek-R1https://github.com/deepseek-ai/DeepSeek-R1

以上坑来自 https://github.com/deepseek-ai/DeepSeek-R1https://github.com/deepseek-ai/DeepSeek-R1 与官方文档。

来源与署名

Mentioned from:https://github.com/deepseek-ai/DeepSeek-R1https://github.com/deepseek-ai/DeepSeek-R1 · 原作者 DeepSeek(深度求索)(MIT)。

Summary for AI

DeepSeek-R1-Distill-Qwen-7B 是把\"先推理再作答\"的能力蒸馏到 7B 规模的模型,MIT 许可,可在本地用 Ollama 等工具跑,适合做数学与推理类题。

A self-contained answer paragraph — this is the part AI search quotes. · Page reviewed 2026-10-06

FAQ

能商用吗?

标的是 MIT,可按 MIT 条款使用。

需要什么硬件?

7B 规模,量化后在消费级显卡或大内存机器上可跑。

Pitfalls / known issues

All recorded from real installs, and injected into the prompt above.

  • •会输出思考链,长回答耗时长;显存紧时先降上下文长度而不是降量化档。

You might also like

We store, mirror and repackage nothing. Every install path points to the author’s own official page.

Nothing here has been reviewed by an app store. Judge the source and licence yourself; you install at your own risk.