DeepSeek 本地部署教程 Windows 新手用 Ollama 跑起来 5 个常见问题
<div class="ce-block ce-block--focused" data-id="oL65WoDSoW" ><div class="ce-block__content">
<div class="cdx-block image-tool image-tool--filled ">
<div class="image-tool__image">
<div class="image-tool__image-preloader" style=""></div>
<img id="aimg_oL65WoDSoW" class="image-tool__image-picture _zoom" src="https://bbs.gpt.com.cn/data/attachment/forum/202608/05/144148himm9clw7i9cqdbc.png" title="" alt="" data-aid="2660"/>
</div>
<div class="cdx-input image-tool__caption" data-placeholder=""></div>
</div>
</div>
</div><div class="ce-block ce-block--focused" data-id="3jyLDAFuRH" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">如果你最近也在找 DeepSeek 本地部署的方法，最容易卡住的地方通常就那几个。装什么，怎么选模型，命令怎么跑，下载慢不慢，内存够不够。把这几件事捋顺，Windows 上把 DeepSeek 跑起来并不难。</span></div>
</div>
</div><div class="ce-block" data-id="sdT86Kx8m5" >
<div class="ce-block__content" style="">
<h2 class="ce-header ce-header--left">一 先把思路捋直</h2>
</div>
</div><div class="ce-block ce-block--focused" data-id="SMBOJvsm4f" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">如果你是第一次碰本地部署，先别急着看一堆术语。你只要记住一件事就够了，Ollama 负责把模型装进电脑里，DeepSeek 负责回答问题。前者像工具，后者像内容。工具装对了，后面的路就顺了。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="-xiR9z3S0i" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">很多人一开始会被网上的一键安装工具带跑偏，看到界面花里胡哨，心里先热一半。其实论坛里最稳的写法，还是把最常见的这条路讲清楚。读者搜的是 DeepSeek 本地部署，不是某个按钮长什么样。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="eoVx_G1Vb9" >
<div class="ce-block__content">
<div class="cdx-block image-tool image-tool--filled ">
<div class="image-tool__image">
<div class="image-tool__image-preloader" style=""></div>
<img id="aimg_eoVx_G1Vb9" class="image-tool__image-picture _zoom" src="https://bbs.gpt.com.cn/data/attachment/forum/202608/05/144205enadofbvrusdbv7d.png" title="" alt="" data-aid="2661"/>
</div>
<div class="cdx-input image-tool__caption" data-placeholder=""></div>
</div>
</div>
</div><div class="ce-block" data-id="vYc0EmeG4O" >
<div class="ce-block__content" style="">
<h2 class="ce-header ce-header--left">二 电脑先别硬上大模型</h2>
</div>
</div><div class="ce-block ce-block--focused" data-id="vAsGo6bvlC" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">本地部署最容易踩坑的地方，不在安装，而在选模型。你要是电脑内存一般，先从 7B 开始最稳。它更适合拿来试流程，先确认能不能跑起来，再谈效果。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="GJUx_8L_I4" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">14B 的体验通常会更像样一点，但对机器要求也高。32B 往上就别急着碰了，很多普通电脑会直接吃不住。新手最好的思路，不是一步到位，而是先跑通，再往上试。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="lKv9Cjjwj1" >
<div class="ce-block__content">
<div class="cdx-block image-tool image-tool--filled ">
<div class="image-tool__image">
<div class="image-tool__image-preloader" style=""></div>
<img id="aimg_lKv9Cjjwj1" class="image-tool__image-picture _zoom" src="https://bbs.gpt.com.cn/data/attachment/forum/202608/05/144221ol88xxeppxx1j42j.png" title="" alt="" data-aid="2662"/>
</div>
<div class="cdx-input image-tool__caption" data-placeholder=""></div>
</div>
</div>
</div><div class="ce-block" data-id="cx9VpnOdY_" >
<div class="ce-block__content" style="">
<h2 class="ce-header ce-header--left">三 安装 Ollama 不难，难的是别跳步骤</h2>
</div>
</div><div class="ce-block ce-block--focused" data-id="HrP5EBAD1H" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">安装 Ollama 的过程其实很直。去官网下 Windows 版本，按提示装好，装完以后去命令行里看看它在不在。能认出来，说明这一步已经过了。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="PUMe9LVZ9h" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">这里最怕的是图快。很多人只看见安装按钮亮了，就觉得已经结束，结果后面模型拉不下来，或者命令行里根本没反应。你只要记住，安装完成不等于可以直接对话。真正能不能跑，还得看后面的模型下载和启动。</span></div>
</div>
</div><div class="ce-block" data-id="wxaBFdw2AQ" >
<div class="ce-block__content" style="">
<h2 class="ce-header ce-header--left">四 模型页看懂了，后面就轻松</h2>
</div>
</div><div class="ce-block ce-block--focused" data-id="g5EJymMGDV" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">很多教程会把模型页贴得很满，数字也多，看起来像在讲参数，实际上你只要盯住一件事，自己机器能扛多大。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="-1n3Nj08Yb" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">如果是纯新手，先选小一点的版本。别一上来就盯着最大的。模型越大，下载越慢，对内存和显存的要求也越高。你的目标不是一次选对所有答案，而是先让它顺利跑起来。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="KwjGfCiQJL" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">模型页通常会给你一条运行命令，你直接复制就行。别自己临时改版本号，也别把字符输错。很多看起来像报错的问题，其实只是少了一个字符。</span></div>
</div>
</div><div class="ce-block" data-id="5fuq--wGt2" >
<div class="ce-block__content" style="">
<h2 class="ce-header ce-header--left">五 真的跑起来以后，先做一个最简单的测试</h2>
</div>
</div><div class="ce-block ce-block--focused" data-id="to7a2zvm_h" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">模型下载完以后，命令行里会开始加载。这个过程看上去像没动静，其实很多时候是在后台忙。等它提示成功，再问一句最普通的话，比如让它介绍自己，或者随便打个招呼。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="I723C-Lq16" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">这一步很重要。因为只有到了这里，你才算是真的把 DeepSeek 本地跑起来了。前面的安装，下载，选择模型，都只是准备工作。能正常回话，才说明这条链路已经通了。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="Pcj9BMJOCa" >
<div class="ce-block__content">
<div class="cdx-block image-tool image-tool--filled ">
<div class="image-tool__image">
<div class="image-tool__image-preloader" style=""></div>
<img id="aimg_Pcj9BMJOCa" class="image-tool__image-picture _zoom" src="https://bbs.gpt.com.cn/data/attachment/forum/202608/05/144245iupoo9wnjqpoluhu.png" title="" alt="" data-aid="2663"/>
</div>
<div class="cdx-input image-tool__caption" data-placeholder=""></div>
</div>
</div>
</div><div class="ce-block" data-id="XDDoeDFzfs" >
<div class="ce-block__content" style="">
<h2 class="ce-header ce-header--left">六 新手最容易卡住的 5 个地方</h2>
</div>
</div><div class="ce-block ce-block--focused" data-id="Py4wIfDe4T" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">第一个是下载慢。模型本来就大，慢不一定是你错了，先别慌。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="Naj6M3-wlz" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">第二个是内存不够。机器一般的话，先换小模型，不要硬撑。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="fWLfz_GQAD" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">第三个是命令输错。模型名，版本号，空格，这些地方都很容易看漏。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="0BwAr39LRc" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain" style="box-sizing: border-box;">第四个是装完就以为结束。安装只是开始，模型跑通才算完成。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="-r0JY3tYPo" >
<div class="ce-block__content">
<div class="ce-paragraph cdx-block ce-paragraph--left"><span md-inline="plain" class="md-plain md-expand" style="box-sizing: border-box;">第五个是第一次失败就想放弃。本地部署本来就会来回试两次，尤其是新手，碰一下小问题很正常。</span></div>
</div>
</div><div class="ce-block ce-block--focused" data-id="CGAmdV41Ia" >
<div class="ce-block__content">
<div class="cdx-block image-tool image-tool--filled ">
<div class="image-tool__image">
<div class="image-tool__image-preloader" style=""></div>
<img id="aimg_CGAmdV41Ia" class="image-tool__image-picture _zoom" src="https://bbs.gpt.com.cn/data/attachment/forum/202608/05/144258a070i4466h66z14s.png" title="" alt="" data-aid="2664"/>
</div>
<div class="cdx-input image-tool__caption" data-placeholder=""></div>
</div>
</div>
</div><style type="text/css">
.ce-block {
margin-bottom: 20px;
}
.ce-block__content,.ce-toolbar__content {
/* max-width:calc(100% - 50px) */
margin-left: auto;
margin-right: auto;
}
.image-tool {
--bg-color: #cdd1e0;
--front-color: #388ae5;
--border-color: #e8e8eb;
}
.image-tool__image {
border-radius: 3px;
overflow: hidden;
margin-bottom: 10px;
}
.image-tool__image-picture {
max-width: 100%;
vertical-align: bottom;
display: block;
margin-left: auto;
margin-right: auto;
}
.image-tool__image-preloader {
width: 50px;
height: 50px;
border-radius: 50%;
background-size: cover;
margin: auto;
position: relative;
background-color: #cdd1e0;
background-position: center center;
}
.image-tool__image-preloader::after {
content: "";
position: absolute;
z-index: 3;
width: 60px;
height: 60px;
border-radius: 50%;
border: 2px solid #cdd1e0;
border-top-color: #388ae5;
left: 50%;
top: 50%;
margin-top: -30px;
margin-left: -30px;
animation: image-preloader-spin 2s infinite linear;
box-sizing: border-box;
}
.image-tool__caption::before {
position: absolute !important;
content: attr(data-placeholder);
color: #707684;
font-weight: normal;
display: none;
}
.image-tool__caption:empty::before {
display: block;
}
.image-tool__caption:empty:focus::before {
display: none;
}
.image-tool--empty .image-tool__image {
display: none;
}
.image-tool--empty .image-tool__caption, .image-tool--loading .image-tool__caption {
display: none;
}
.image-tool .cdx-button {
display: flex;
align-items: center;
justify-content: center;
}
.image-tool .cdx-button svg {
height: auto;
margin: 0 6px 0 0;
}
.image-tool--filled .cdx-button {
display: none;
}
.image-tool--filled .image-tool__image-preloader {
display: none;
}
.image-tool--loading .image-tool__image {
min-height: 200px;
display: flex;
border: 1px solid #e8e8eb;
background-color: #fff;
}
.image-tool--loading .image-tool__image-picture {
display: none;
}
.image-tool--loading .cdx-button {
display: none;
}
/**
* Tunes
* ----------------
*/
.image-tool--withBorder .image-tool__image {
border: 1px solid #e8e8eb;
}
.image-tool--withBackground .image-tool__image {
padding: 15px;
background: #cdd1e0;
}
.image-tool--withBackground .image-tool__image-picture {
max-width: 60%;
margin: 0 auto;
}
.image-tool--stretched .image-tool__image-picture {
width: 100%;
}
.image-tool__caption {
text-align: center;
font-size: 14px;
color: #a3a3a3;
}
@keyframes image-preloader-spin {
0% {
transform: rotate(0deg);
}
100% {
transform: rotate(360deg);
}
}
</style><style type="text/css">
.ce-block {
margin-bottom: 20px;
}
.ce-block__content,.ce-toolbar__content {
/* max-width:calc(100% - 50px) */
margin-left: auto;
margin-right: auto;
}
.ce-paragraph {
line-height: 1.6em;
outline: none;
text-indent: 2em;
font-size: 16px;
}
.ce-paragraph--right {
text-align: right;
}
.ce-paragraph--center {
text-align: center;
}
.ce-paragraph--left {
text-align: left;
}
.ce-paragraph--justify {
text-align: justify;
}
.ce-paragraph-text-indent {
text-align: justify;
}
.ce-paragraph:empty::before{
content: attr(data-placeholder);
color: #707684;
font-weight: normal;
opacity: 0;
}
/** Show placeholder at the first paragraph if Editor is empty */
.codex-editor--empty .ce-block:first-child .ce-paragraph:empty::before {
opacity: 1;
}
.codex-editor--toolbox-opened .ce-block:first-child .ce-paragraph:empty::before,
.codex-editor--empty .ce-block:first-child .ce-paragraph:empty:focus::before {
opacity: 0;
}
.ce-paragraph p:first-of-type{
margin-top: 0;
}
.ce-paragraph p:last-of-type{
margin-bottom: 0;
}
.svg-icon {
width: 1em;
height: 1em;
}
.svg-icon path,
.svg-icon polygon,
.svg-icon rect {
fill: #4691f6;
}
.svg-icon circle {
stroke: #4691f6;
stroke-width: 1;
}
</style><style type="text/css">
.ce-block {
margin-top: 20px;
margin-bottom: 20px;
}
.ce-block__content,.ce-toolbar__content {
/* max-width:calc(100% - 50px) */
margin-left: auto;
margin-right: auto;
}
/**
* Plugin styles
*/
.ce-header {
position: relative;
padding: 1px 0px 1px 15px;
margin: 0;
line-height: 1.25em;
outline: none;
margin-bottom: 10px;
}
.ce-header p,
.ce-header div {
padding: 0 !important;
margin: 0 !important;
}
.ce-header::before {
content: "";
background-color: #3e8fe3;
width: 6px;
height: 100%;
position: absolute;
left: 0;
-webkit-border-radius: 3px;
-moz-border-radius: 3px;
border-radius: 3px;
}
/**
* Styles for Plugin icon in Toolbar
*/
.ce-header__icon {
}
.ce-header::before {
position: absolute;
content: attr(data-placeholder);
color: #707684;
font-weight: normal;
display: none;
cursor: text;
}
.ce-header:empty::before {
display: block;
}
.ce-header:empty:focus::before {
display: none;
}
/* FontSize */
h1.ce-header {
font-size: 2.0em;
}
h2.ce-header {
font-size: 1.7em;
}
h3.ce-header {
font-size: 1.4em;
}
h4.ce-header {
font-size: 1.15em;
}
h5.ce-header {
font-size: 0.95em;
}
h6.ce-header {
font-size: 0.8em;
}
/* Alignment*/
.ce-header--right {
text-align: right;
}
.ce-header--center {
text-align: center;
}
.ce-header--left {
text-align: left;
}
.ce-header--justify {
text-align: justify;
}
</style><style type="text/css">
.inline-code {
background: rgba(250, 239, 240, 0.78);
color: #b44437;
padding: 3px 4px;
border-radius: 5px;
margin: 0 1px;
font-family: inherit;
font-size: 0.86em;
font-weight: 500;
letter-spacing: 0.3px;
}
</style>
页:
[1]