You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
1 lines
16 KiB
1 lines
16 KiB
<!doctypehtml><html lang=zh-CN><meta charset=UTF-8><meta content=width=device-width name=viewport><meta content=#222 name=theme-color><meta content="Hexo 7.1.0" name=generator><link href=https://cdnjs.cloudflare.com rel=preconnect><link href=/images/apple-touch-icon-next.png rel=apple-touch-icon sizes=180x180><link href=/images/favicon-32x32-next.png rel=icon sizes=32x32 type=image/png><link href=/images/favicon-16x16-next.png rel=icon sizes=16x16 type=image/png><link color=#222 href=/images/logo.svg rel=mask-icon><meta content=2X6S9P7CAjXjVvw8YyQR8pCu-B0oEu7O9quLgxXuWyA name=google-site-verification><meta content=dV8JGNzi0c name=baidu-site-verification><script>!function(){var t=!1;function e(){var e;t||(t=!0,(e=document.createElement("script")).setAttribute("data-ad-client","ca-pub-7480618470784058"),e.async=!0,e.src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js",document.head.appendChild(e))}function a(){"requestIdleCallback"in window?window.requestIdleCallback(e,{timeout:5e3}):window.setTimeout(e,5e3)}"complete"===document.readyState?a():window.addEventListener("load",a,{once:!0})}()</script><link href=/css/main.css rel=stylesheet><link crossorigin=anonymous href=https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.5.0/css/all.min.css integrity=sha256-yIDrPSXHZdOZhAqiBP7CKzIwMQmRCJ8UeB8Jo17YC4o= rel=stylesheet><link crossorigin=anonymous href=https://cdnjs.cloudflare.com/ajax/libs/fancyapps-ui/5.0.28/fancybox/fancybox.css integrity=sha256-6cQIC71/iBIYXFK+0RHAvwmjwWzkWd+r7v/BX3/vZDc= rel=stylesheet><script class=next-config data-name=main type=application/json>{"hostname":"nicksxs.me","root":"/","images":"/images","scheme":"Pisces","darkmode":false,"version":"8.19.1","exturl":false,"sidebar":{"position":"left","display":"post","padding":18,"offset":12},"copycode":{"enable":true,"style":"default"},"fold":{"enable":false,"height":500},"bookmark":{"enable":false,"color":"#222","save":"auto"},"mediumzoom":false,"lazyload":true,"pangu":false,"comments":{"style":"tabs","active":null,"storage":true,"lazyload":true,"nav":null},"stickytabs":false,"motion":{"enable":false,"async":false,"transition":{"menu_item":"fadeInDown","post_block":"fadeIn","post_header":"fadeInDown","post_body":"fadeInDown","coll_header":"fadeInLeft","sidebar":"fadeInUp"}},"prism":false,"i18n":{"placeholder":"搜索...","empty":"没有找到任何搜索结果：${query}","hits_time":"找到 ${hits} 个搜索结果（用时 ${time} 毫秒）","hits":"找到 ${hits} 个搜索结果"},"algolia":{"appID":"663Q99OQQD","apiKey":"e461a1371d12cec1491c1153b288a9ed","indexName":"nicksxs","hits":{"per_page":10}}}</script><script src=/js/config.js></script><meta content="输入显卡型号、显存、内存、模型参数量、量化和上下文长度，估算显存占用并生成 llama.cpp、vLLM 或 FreeToken 启动参数。" name=description><meta content=website property=og:type><meta content=大模型本地运行参数生成器 property=og:title><meta content=https://nicksxs.me/tools/llm-config/index.html property=og:url><meta content="Nicksxs's Blog" property=og:site_name><meta content="输入显卡型号、显存、内存、模型参数量、量化和上下文长度，估算显存占用并生成 llama.cpp、vLLM 或 FreeToken 启动参数。" property=og:description><meta content=zh_CN property=og:locale><meta content=2026-09-05T14:20:00.000Z property=article:published_time><meta content=2026-09-05T14:20:00.000Z property=article:modified_time><meta content=Nicksxs property=article:author><meta content=Nicksxs,Java,JVM,字节码,Arthas,大模型推理,LLM,Agent property=article:tag><meta content=summary name=twitter:card><link href=https://nicksxs.me/tools/llm-config/ rel=canonical><script class=next-config data-name=page type=application/json>{"sidebar":"","isHome":false,"isPost":false,"lang":"zh-CN","comments":"","permalink":"https://nicksxs.me/tools/llm-config/index.html","path":"tools/llm-config/index.html","title":"大模型本地运行参数生成器"}</script><script class=next-config data-name=calendar type=application/json>""</script><title>大模型本地运行参数生成器 | Nicksxs's Blog</title><script async src=https://www.googletagmanager.com/gtag/js?id=UA-61358619-1></script><script class=next-config data-name=google_analytics type=application/json>{"tracking_id":"UA-61358619-1","only_pageview":false,"measure_protocol_api_secret":null}</script><script src=/js/third-party/analytics/google-analytics.js></script><script src=/js/third-party/analytics/baidu-analytics.js></script><script async src=https://hm.baidu.com/hm.js?20f33b3c0c0eff9b1522999c0015646d></script><noscript><link href=/css/noscript.css rel=stylesheet></noscript><link title="Nicksxs's Blog" href=/atom.xml rel=alternate type=application/atom+xml><body itemscope itemtype=http://schema.org/WebPage><div class=headband></div><main class=main><div class=column><header class=header itemscope itemtype=http://schema.org/WPHeader><div class=site-brand-container><div class=site-nav-toggle><div aria-label=切换导航栏 class=toggle role=button><span class=toggle-line></span><span class=toggle-line></span><span class=toggle-line></span></div></div><div class=site-meta><a class=brand href=/ rel=start><i class=logo-line></i><p class=site-title>Nicksxs's Blog</p><i class=logo-line></i></a><p class=site-subtitle itemprop=description>Java 运行时、生产诊断与 AI 工程实践</div><div class=site-nav-right><div class="toggle popup-trigger" aria-label=搜索 role=button><i class="fa fa-search fa-fw fa-lg"></i></div></div></div><nav class=site-nav><ul class="main-menu menu"><li class="menu-item menu-item-home"><a href=/ rel=section><i class="fa fa-home fa-fw"></i>首页</a><li class="menu-item menu-item-专题"><a href=/topics/ rel=section><i class="fa fa-layer-group fa-fw"></i>专题</a><li class="menu-item menu-item-工具"><a href=/tools/ rel=section><i class="fa fa-toolbox fa-fw"></i>工具</a><li class="menu-item menu-item-about"><a href=/about/ rel=section><i class="fa fa-user fa-fw"></i>关于我</a><li class="menu-item menu-item-tags"><a href=/tags/ rel=section><i class="fa fa-tags fa-fw"></i>标签</a><li class="menu-item menu-item-categories"><a href=/categories/ rel=section><i class="fa fa-th fa-fw"></i>分类</a><li class="menu-item menu-item-archives"><a href=/archives/ rel=section><i class="fa fa-archive fa-fw"></i>归档</a><li class="menu-item menu-item-search"><a class=popup-trigger role=button><i class="fa fa-search fa-fw"></i>搜索</a></ul></nav><div class=search-pop-overlay><div class="popup search-popup"><div class=search-header><span class=search-icon><i class="fa fa-search"></i></span><div class=search-input-container></div><span class=popup-btn-close role=button><i class="fa fa-times-circle"></i></span></div><div class=search-result-container><div class=algolia-stats><hr></div><div class=algolia-hits></div><div class=algolia-pagination></div></div></div></div></header></div><div class="main-inner page posts-expand"><div class=tool-workspace data-tool=llm-config data-tool-group=ai lang=zh-CN><nav aria-label=面包屑 class=tool-breadcrumb><a href=/tools/><i class="fa fa-arrow-left" aria-hidden=true></i> 在线工具箱</a></nav><header class=tool-header><div><span class=tool-eyebrow>BROWSER-ONLY DIAGNOSTICS</span><h1>大模型本地运行参数生成器</h1><p>输入显卡型号、显存、内存、模型参数量、量化和上下文长度，估算显存占用并生成 llama.cpp、vLLM 或 FreeToken 启动参数。</div><div class=tool-local-badge><i class="fa fa-shield-halved" aria-hidden=true></i><span>本地处理<small>不会上传文件</small></span></div></header><section class="tool-panel tool-input-panel" aria-labelledby=llm-input-title><div class=tool-panel-heading><div><h2 id=llm-input-title>填写硬件与模型配置</h2><p>先判断能否装下权重与 KV Cache，再生成偏稳定的起步参数。</div><button class="tool-button tool-button-quiet" data-action=sample type=button>6GB 显存示例</button></div><div class=tool-config-section><h3>运行环境</h3><div class=tool-config-grid><label class=tool-field><span>推理后端</span><select data-config=runtime><option value=auto>自动选择<option value=llama>llama.cpp<option value=vllm>vLLM<option value=freetoken>FreeToken</select></label><label class=tool-field><span>显卡型号</span><select data-config=gpu><option value=rtx3060-6>RTX 3060 6GB<option value=rtx4060-8>RTX 4060 8GB<option value=rtx4070-12>RTX 4070 12GB<option value=rtx3090-24>RTX 3090 24GB<option value=rtx4090-24>RTX 4090 24GB<option value=rtx5090-32>RTX 5090 32GB<option value=a100-40>A100 40GB<option value=a100-80>A100 80GB<option value=h100-80>H100 80GB<option value=apple-24>Apple Silicon 24GB 统一内存<option value=amd-16>AMD GPU 16GB<option value=custom>自定义</select></label><label class=tool-field><span>GPU 数量</span><input data-config=gpuCount max=8 min=1 step=1 type=number value=1></label><label class=tool-field><span>单卡显存</span><div class=tool-unit-input><input data-config=vram min=1 step=1 type=number value=6><em>GB</em></div></label><label class=tool-field><span>系统内存</span><div class=tool-unit-input><input data-config=ram min=4 step=4 type=number value=32><em>GB</em></div></label><label class=tool-field><span>CPU 物理核心</span><input data-config=cores max=256 min=1 step=1 type=number value=8></label><label class=tool-field><span>硬盘可用空间</span><div class=tool-unit-input><input data-config=disk min=1 step=10 type=number value=100><em>GB</em></div></label></div></div><div class=tool-config-section><h3>模型与负载</h3><div class=tool-config-grid><label class=tool-field><span>模型结构</span><select data-config=architecture><option value=dense>Dense 稠密模型<option value=moe>MoE 混合专家</select></label><label class=tool-field><span>总参数量</span><div class=tool-unit-input><input data-config=params min=0.5 step=0.5 type=number value=7><em>B</em></div></label><label class=tool-field data-active-field hidden><span>激活参数量</span><div class=tool-unit-input><input data-config=activeParams min=0.5 step=0.5 type=number value=3><em>B</em></div></label><label class=tool-field><span>权重量化</span><select data-config=quant><option value=bf16>BF16 / FP16<option value=fp8>FP8<option value=q8>INT8 / Q8<option value=q6>Q6<option value=q5>Q5<option selected value=q4>Q4<option value=q3>Q3</select></label><label class=tool-field><span>模型格式</span><select data-config=format><option selected value=gguf>GGUF<option value=safetensors>Safetensors<option value=awq>AWQ<option value=gptq>GPTQ<option value=ftw>FreeToken FTW</select></label><label class=tool-field><span>上下文长度</span><select data-config=context><option value=4096>4K<option selected value=8192>8K<option value=16384>16K<option value=32768>32K<option value=65536>64K<option value=131072>128K</select></label><label class=tool-field><span>并发请求</span><select data-config=concurrency><option selected value=1>1<option value=2>2<option value=4>4<option value=8>8<option value=16>16</select></label><label class=tool-field><span>模型路径 / HF ID</span><input data-config=model value=/models/model.gguf></label></div></div><div class=tool-actions><button class="tool-button tool-button-primary" data-action=generate type=button><i class="fa fa-wand-magic-sparkles" aria-hidden=true></i> 生成推荐参数</button><span class=tool-hint>结果是安全起点，不替代模型实测和后端启动日志</span></div></section><section aria-live=polite class=tool-results data-results hidden><div class=tool-section-heading><div><span>INFERENCE PLAN</span><h2>推荐方案</h2></div><button class="tool-button tool-button-quiet" data-action=copy type=button>复制方案</button></div><div class=tool-llm-verdict data-verdict></div><div class=tool-metrics data-metrics></div><div class="tool-split tool-llm-output"><div><h3>启动命令</h3><pre class=tool-output><code data-command></code></pre></div><div><h3>判断与限制</h3><div class=tool-findings data-findings></div></div></div><div class=tool-assumptions><strong>估算口径</strong><p data-assumptions><p>参数名以运行时当前版本为准。生成命令前建议先执行对应程序的 <code>--help</code>。</div><nav aria-label=运行时参数文档 class=tool-reference-links><span>参数文档</span><a href=https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md rel=noopener target=_blank>llama.cpp</a><a href=https://docs.vllm.ai/en/latest/configuration/engine_args/ rel=noopener target=_blank>vLLM</a><a href=https://github.com/FlashML-org/FreeToken/blob/main/docs/cli.md rel=noopener target=_blank>FreeToken</a></nav></section><section class=tool-empty data-empty><i class="fa fa-microchip" aria-hidden=true></i><strong>等待硬件配置</strong><span>默认值代表单卡 6GB 显存、32GB 内存运行 7B Q4 模型。</span></section><aside aria-label=相关工具 class=tool-more><span>其他工具</span></aside><script defer src=/tools/llm-config.js></script></div></div></main><footer class=footer><div class=footer-inner><div class=beian><a href=https://beian.miit.gov.cn/ rel=noopener target=_blank>浙ICP备16002580号-2 </a><img alt src=/uploads/beian.png><a href=https://beian.mps.gov.cn/#/query/webSearch?code=33010602011094 rel=noopener target=_blank>浙公网安备 33010602011094号</a></div><div class=copyright>© <span itemprop=copyrightYear>2026</span><span class=with-love><i class="fa fa-heart"></i> </span><span class=author itemprop=copyrightHolder>Nicksxs</span></div></div></footer><div aria-label=返回顶部 class=back-to-top role=button><i class="fa fa-arrow-up fa-lg"></i><span>0%</span></div><a aria-label="在 GitHub 上关注我" title="在 GitHub 上关注我" class=github-corner href=https://github.com/nicksxs rel=noopener target=_blank><svg viewbox="0 0 250 250" aria-hidden=true height=80 width=80><path d="M0,0 L115,115 L130,115 L142,142 L250,250 L250,0 Z"></path><path d="M128.3,109.0 C113.8,99.7 119.0,89.6 119.0,89.6 C122.0,82.7 120.5,78.6 120.5,78.6 C119.2,72.0 123.4,76.3 123.4,76.3 C127.3,80.9 125.5,87.3 125.5,87.3 C122.9,97.6 130.6,101.9 134.4,103.2" style="transform-origin:130px 106px" class=octo-arm fill=currentColor></path><path d="M115.0,115.0 C114.9,115.1 118.7,116.5 119.8,115.4 L133.7,101.6 C136.9,99.2 139.9,98.4 142.2,98.6 C133.8,88.0 127.5,74.4 143.8,58.0 C148.5,53.4 154.0,51.2 159.7,51.0 C160.3,49.4 163.2,43.6 171.4,40.1 C171.4,40.1 176.1,42.5 178.8,56.2 C183.1,58.6 187.2,61.8 190.9,65.4 C194.5,69.0 197.7,73.2 200.1,77.6 C213.8,80.2 216.3,84.9 216.3,84.9 C212.7,93.1 206.9,96.0 205.4,96.6 C205.1,102.4 203.0,107.8 198.3,112.5 C181.9,128.9 168.3,122.5 157.7,114.1 C157.9,116.9 156.7,120.9 152.7,124.9 L141.0,136.5 C139.8,137.7 141.6,141.9 141.8,141.8 Z" class=octo-body fill=currentColor></path></svg></a><noscript><div class=noscript-warning>Theme NexT works best with JavaScript enabled</div></noscript><script crossorigin=anonymous integrity=sha256-XL2inqUJaslATFnHdJOi9GfQ60on8Wx1C2H8DYiN1xY= src=https://cdnjs.cloudflare.com/ajax/libs/animejs/3.2.1/anime.min.js></script><script crossorigin=anonymous integrity=sha256-ytMJGN3toR+a84u7g7NuHm91VIR06Q41kMWDr2pq7Zo= src=https://cdnjs.cloudflare.com/ajax/libs/fancyapps-ui/5.0.28/fancybox/fancybox.umd.js></script><script crossorigin=anonymous integrity=sha256-mOFREFhqmHeQbXpK2lp4nA3qooVgACfh88fpJftLBbc= src=https://cdnjs.cloudflare.com/ajax/libs/lozad.js/1.16.0/lozad.min.js></script><script src=/js/comments.js></script><script src=/js/utils.js></script><script src=/js/next-boot.js></script><script data-algolia-integrity=sha256-DABVk+hYj0mdUzo+7ViJC6cwLahQIejFvC+my2M/wfM= data-algolia-src=https://cdnjs.cloudflare.com/ajax/libs/algoliasearch/4.20.0/algoliasearch-lite.umd.js data-instant-search-integrity=sha256-9242vN47QUX50UG5Gf5XDO1YREWCEJRyXHofh5fsl24= data-instant-search-src=https://cdnjs.cloudflare.com/ajax/libs/instantsearch.js/4.60.0/instantsearch.production.min.js data-search-src=/js/third-party/search/algolia-search.js src=/js/third-party/search/algolia-search-loader.js></script><script src=/js/third-party/fancybox.js></script><script data-cloudflare-page-counter-config type=application/json>{"enable":true,"endpoint":"https://counter.nicksxs.me","site":"nicksxs","local_cache":true,"timeout":5000,"icon":"far fa-eye","item_text":true}</script><script src=/js/cloudflare-page-counter.js></script><script class=next-config data-name=disqus type=application/json>{"enable":true,"shortname":"nicksxs","count":false,"i18n":{"disqus":"disqus"}}</script><script src=/js/third-party/comments/disqus.js></script>
|