[{"data":1,"prerenderedAt":996},["ShallowReactive",2],{"header-counts":3,"footer-counts":6,"compare-gpt4all-vs-ollama":8,"compare-a-gpt4all":9,"compare-b-ollama":495},{"tools":4,"reviews":5},98,27,{"tools":4,"reviews":5,"playbooks":7,"news":5},22,null,{"id":10,"title":11,"alternatives":12,"api_compatible":8,"body":16,"category":460,"chinese_friendly":449,"cover":461,"description":462,"domestic":463,"extension":464,"faq":8,"free":463,"github":441,"languages":465,"lastVerified":467,"meta":468,"models":8,"navigation":469,"notSuitable":8,"opensource":469,"path":470,"pillar":471,"platforms":472,"priceTable":8,"pricing":476,"published":477,"relatedPlaybooks":8,"relatedReviews":8,"score":478,"self_host":463,"seo":481,"seoTitle":482,"slug":483,"sources":484,"stem":487,"suitable":8,"tagline":488,"tags":489,"updated":467,"verdict":493,"website":433,"__hash__":494},"tools\u002Ftools\u002Fcoding\u002Flocal\u002Fgpt4all.md","GPT4All",[13,14,15],"coding\u002Flocal\u002Follama","coding\u002Flocal\u002Flm-studio","coding\u002Flocal\u002Fjan",{"type":17,"value":18,"toc":444},"minimark",[19,24,33,36,39,91,94,100,133,136,140,148,165,170,187,190,215,218,316,319,351,355,378,382,388,394,400,403,419,422,427],[20,21,23],"h2",{"id":22},"tldr","TL;DR",[25,26,27,28,32],"p",{},"GPT4All 是 Nomic AI 出品的本地 LLM 推理工具，最大卖点是",[29,30,31],"strong",{},"CPU 也能跑","——没有独立显卡的普通笔记本 \u002F 办公本照样运行本地大模型。MIT 开源，桌面客户端一键下载 GGUF 模型，开箱即用。适合无 GPU 设备、隐私优先、轻量本地推理场景。",[25,34,35],{},"适合：没有独立 GPU 的笔记本 \u002F 办公本用户、需要完全离线本地推理、隐私敏感场景、轻量聊天 \u002F 文档处理。不适合：需要高速推理（CPU 太慢）、需要 OpenAI 兼容 API 给应用接入（用 Ollama）、需要大模型（32B+，CPU 跑不动）。",[20,37,38],{"id":38},"核心能力",[40,41,42,49,55,61,67,73,79,85],"ul",{},[43,44,45,48],"li",{},[29,46,47],{},"CPU 推理","：基于 llama.cpp 优化，纯 CPU 跑 7B 量化模型，无需 GPU",[43,50,51,54],{},[29,52,53],{},"一键下载模型","：内置模型库，点击即下载 GGUF 格式模型，自动配置",[43,56,57,60],{},[29,58,59],{},"桌面客户端","：跨平台 GUI（Win \u002F Mac \u002F Linux），聊天界面开箱即用",[43,62,63,66],{},[29,64,65],{},"LocalDocs（RAG）","：内置文档问答功能，拖入 PDF \u002F 文档即可基于本地文档聊天",[43,68,69,72],{},[29,70,71],{},"OpenAI 兼容 API","：内置 Local Server，暴露 OpenAI 兼容端点供应用调用",[43,74,75,78],{},[29,76,77],{},"模型库丰富","：Llama \u002F Qwen \u002F Mistral \u002F Phi \u002F GPT-OSS 等主流开源模型可选",[43,80,81,84],{},[29,82,83],{},"GPU 加速（可选）","：有 GPU 时自动启用，速度提升数倍",[43,86,87,90],{},[29,88,89],{},"MIT 开源","：完全免费，可商用，提供 Python \u002F C++ SDK 二次开发",[20,92,93],{"id":93},"价格",[95,96,97],"blockquote",{},[25,98,99],{},"以下信息为 2026-07-30 核实。",[101,102,103,118],"table",{},[104,105,106],"thead",{},[107,108,109,113,115],"tr",{},[110,111,112],"th",{},"方案",[110,114,93],{},[110,116,117],{},"说明",[119,120,121],"tbody",{},[107,122,123,127,130],{},[124,125,126],"td",{},"开源版",[124,128,129],{},"$0",[124,131,132],{},"完整功能，MIT 协议，商用免费",[25,134,135],{},"完全免费。成本在于硬件（CPU \u002F 内存）和你选用的模型。",[20,137,139],{"id":138},"体验与评测资料整理","体验与评测（资料整理）",[95,141,142],{},[25,143,144,145],{},"说明：本节基于官方文档与公开评测整理，非本站独立实测环境，具体数据请以官方为准。\n",[29,146,147],{},"亮点：",[40,149,150,153,156,159,162],{},[43,151,152],{},"纯 CPU 跑 Qwen2.5-7B-Q4 在 i7 笔记本上约 5-8 tok\u002Fs，轻量聊天可用",[43,154,155],{},"LocalDocs 文档问答好用：拖入技术 PDF，直接问问题，完全离线",[43,157,158],{},"模型一键下载体验顺滑，不用手动找 GGUF + 配路径",[43,160,161],{},"有 GPU 时自动加速，RTX 3060 跑 7B 约 30-40 tok\u002Fs",[43,163,164],{},"桌面 GUI 简洁易用，非技术用户也能上手",[25,166,167],{},[29,168,169],{},"踩坑：",[40,171,172,175,178,181,184],{},[43,173,174],{},"CPU 推理速度慢，7B 模型生成一段代码要等 10-20 秒",[43,176,177],{},"内存占用高：7B-Q4 至少需 8GB RAM，13B 需 16GB",[43,179,180],{},"LocalDocs 的 RAG 质量一般，复杂文档检索准确率不高",[43,182,183],{},"OpenAI 兼容 API 功能弱，不如 Ollama 灵活，不支持自定义 Modelfile",[43,185,186],{},"中文模型支持一般，需手动选 Qwen 等中文友好的模型",[20,188,189],{"id":189},"上手",[191,192,193,196,199,202,205,208],"ol",{},[43,194,195],{},"从 gpt4all.io 下载对应平台安装包",[43,197,198],{},"安装后打开桌面客户端",[43,200,201],{},"点击 \"Downloads\" → 选模型（推荐 Qwen2.5-7B-Q4 或 Llama3.1-8B-Q4）",[43,203,204],{},"下载完成后回到 Chat → 选模型 → 开始聊天",[43,206,207],{},"文档问答：LocalDocs → 添加文档文件夹 → 在聊天中勾选引用",[43,209,210,211],{},"API 接入：Settings → 启用 API Server → 端点 ",[212,213,214],"code",{},"http:\u002F\u002Flocalhost:4891\u002Fv1",[20,216,217],{"id":217},"对比",[101,219,220,235],{},[104,221,222],{},[107,223,224,227,229,232],{},[110,225,226],{},"维度",[110,228,11],{},[110,230,231],{},"Ollama",[110,233,234],{},"LM Studio",[119,236,237,249,262,276,289,303],{},[107,238,239,241,244,247],{},[124,240,47],{},[124,242,243],{},"✅ 优化好",[124,245,246],{},"✅",[124,248,246],{},[107,250,251,254,257,260],{},[124,252,253],{},"GUI",[124,255,256],{},"✅ 桌面",[124,258,259],{},"❌ CLI",[124,261,246],{},[107,263,264,267,270,273],{},[124,265,266],{},"模型下载",[124,268,269],{},"✅ 内置库",[124,271,272],{},"✅ CLI",[124,274,275],{},"✅ GUI 库",[107,277,278,281,284,287],{},[124,279,280],{},"OpenAI API",[124,282,283],{},"基础",[124,285,286],{},"强（Modelfile）",[124,288,246],{},[107,290,291,294,297,300],{},[124,292,293],{},"文档 RAG",[124,295,296],{},"✅ LocalDocs",[124,298,299],{},"需配 WebUI",[124,301,302],{},"需插件",[107,304,305,308,311,313],{},[124,306,307],{},"开源",[124,309,310],{},"MIT",[124,312,310],{},[124,314,315],{},"闭源",[20,317,318],{"id":318},"避坑",[40,320,321,327,333,339,345],{},[43,322,323,326],{},[29,324,325],{},"CPU 用户别跑大模型","：13B 以上 CPU 跑基本不可用，坚持 7B 量化",[43,328,329,332],{},[29,330,331],{},"LocalDocs 别放太多文件","：文件多了索引慢且检索质量下降，分批放",[43,334,335,338],{},[29,336,337],{},"API Server 别对公网开","：默认无鉴权，仅本地用",[43,340,341,344],{},[29,342,343],{},"内存不够会崩","：8GB RAM 只能跑 7B-Q4，别勉强 13B",[43,346,347,350],{},[29,348,349],{},"中文场景选 Qwen","：Llama 系列中文能力弱，Qwen \u002F GLM 更合适",[20,352,354],{"id":353},"适合-不适合","适合 \u002F 不适合",[40,356,357,360,363,366,369,372,375],{},[43,358,359],{},"✅ 没有独立 GPU 的笔记本 \u002F 办公本",[43,361,362],{},"✅ 需要完全离线 + 隐私优先的本地推理",[43,364,365],{},"✅ 轻量聊天 \u002F 文档问答场景",[43,367,368],{},"✅ 非技术用户（GUI 友好）",[43,370,371],{},"❌ 需要高速推理（有 GPU 直接 Ollama）",[43,373,374],{},"❌ 需要给应用 \u002F IDE 接入 API（用 Ollama）",[43,376,377],{},"❌ 需要跑大模型（32B+，CPU 跑不动）",[20,379,381],{"id":380},"faq","FAQ",[25,383,384,387],{},[29,385,386],{},"Q: CPU 跑 7B 模型速度能接受吗？","\nA: 看用途。轻量聊天 \u002F 短问答可以接受（5-8 tok\u002Fs）。但代码生成 \u002F 长文本输出等待时间较长（一段代码 10-20 秒）。有 GPU 强烈建议用 GPU。",[25,389,390,393],{},[29,391,392],{},"Q: GPT4All 和 Ollama 怎么选？","\nA: 没 GPU + 要 GUI → GPT4All。有 GPU + 要 API 接入应用 → Ollama。两者底层都基于 llama.cpp，模型格式通用（GGUF）。",[25,395,396,399],{},[29,397,398],{},"Q: LocalDocs 文档问答好用吗？","\nA: 基础可用但 RAG 质量一般。简单 PDF 问答没问题，复杂文档 \u002F 多文件检索准确率不高。专业 RAG 需求建议配 Open WebUI + 向量数据库。",[20,401,402],{"id":402},"相关阅读",[25,404,405,410,411,410,415],{},[406,407,409],"a",{"href":408},"\u002Fcoding\u002Flocal\u002Fjan.html","Jan"," · ",[406,412,414],{"href":413},"\u002Fcoding\u002Flocal\u002Fvllm.html","vLLM",[406,416,418],{"href":417},"\u002Fagent\u002Fdesktop\u002Fopen-interpreter.html","Open Interpreter",[20,420,421],{"id":421},"来源",[95,423,424],{},[25,425,426],{},"本文的价格、版本号与性能数据均参考以下官方渠道整理，可能随时间变动，请以官方实时信息为准。",[40,428,429,437],{},[43,430,431],{},[406,432,436],{"href":433,"rel":434},"https:\u002F\u002Fgpt4all.io",[435],"nofollow","官网",[43,438,439],{},[406,440,443],{"href":441,"rel":442},"https:\u002F\u002Fgithub.com\u002Fnomic-ai\u002Fgpt4all",[435],"GitHub",{"title":445,"searchDepth":446,"depth":446,"links":447},"",3,[448,450,451,452,453,454,455,456,457,458,459],{"id":22,"depth":449,"text":23},2,{"id":38,"depth":449,"text":38},{"id":93,"depth":449,"text":93},{"id":138,"depth":449,"text":139},{"id":189,"depth":449,"text":189},{"id":217,"depth":449,"text":217},{"id":318,"depth":449,"text":318},{"id":353,"depth":449,"text":354},{"id":380,"depth":449,"text":381},{"id":402,"depth":449,"text":402},{"id":421,"depth":449,"text":421},"local","\u002Fimg\u002Ftools\u002Fgpt4all.webp","GPT4All 真实评测：Nomic AI 出品的本地 LLM 推理工具（MIT 协议），支持 CPU 运行无需 GPU，GGUF 格式模型一键下载。跨平台桌面客户端，适合没有独立显卡、需要在普通笔记本上跑本地大模型的用户。",false,"md",[466],"en","2026-07-30",{},true,"\u002Ftools\u002Fcoding\u002Flocal\u002Fgpt4all","coding",[473,474,475],"windows","macos","linux","Free \u002F 开源（MIT）","2026-07-05",{"power":446,"ux":479,"price":480,"cn_support":449,"stability":479},4,5,{"title":11,"description":462},"GPT4All - 本地 LLM 推理引擎评测与使用 | AIHO","coding\u002Flocal\u002Fgpt4all",[485,486],{"title":436,"url":433},{"title":443,"url":441},"tools\u002Fcoding\u002Flocal\u002Fgpt4all","本地 LLM 推理，Nomic AI 出品，支持 CPU 运行",[460,490,491,492],"cpu-inference","opensource","gguf","没有 GPU 也能跑本地大模型的首选，CPU 推理 + 一键下载模型体验顺滑；但推理速度慢、API 能力弱，有 GPU 用户建议直接 Ollama。","oTtyXhNkQBIi7aJI5YJrsiu_c1A81ifErtlA5QOs9UI",{"id":496,"title":231,"alternatives":497,"api_compatible":8,"body":501,"category":460,"chinese_friendly":446,"cover":942,"description":943,"domestic":463,"extension":464,"faq":944,"free":463,"github":8,"languages":957,"lastVerified":8,"meta":958,"models":8,"navigation":469,"notSuitable":8,"opensource":469,"path":959,"pillar":471,"platforms":960,"priceTable":962,"pricing":967,"published":968,"relatedPlaybooks":969,"relatedReviews":8,"score":972,"self_host":469,"seo":973,"seoTitle":974,"slug":13,"sources":975,"stem":983,"suitable":8,"tagline":984,"tags":985,"updated":978,"verdict":993,"website":994,"__hash__":995},"tools\u002Ftools\u002Fcoding\u002Flocal\u002Follama.md",[14,498,499,500],"coding\u002Flocal\u002Fopen-webui","coding\u002Flocal\u002Fcherry-studio","coding\u002Flocal\u002Flobe-chat",{"type":17,"value":502,"toc":930},[503,505,512,515,517,586,588,591,595,599,619,623,654,656,690,692,818,820,852,854,877,879,905,907],[20,504,23],{"id":22},[25,506,507,508,511],{},"Ollama 是本地 LLM 的 Daemon 事实标准——后台跑、暴露 REST API（11434）+ CLI、Modelfile 配置、GGUF 一站式。MIT 开源，跨 Win \u002F Mac \u002F Linux。0.19+ 起 Mac M 系列底层切 MLX 推理。模型库覆盖 Llama \u002F Qwen \u002F DeepSeek \u002F Gemma \u002F Mistral 等主流开源模型，",[212,509,510],{},"ollama pull"," 一键拉。",[25,513,514],{},"适合：给 Cursor \u002F Cline \u002F Continue \u002F Open WebUI 接本地 OpenAI 兼容 endpoint、个人 \u002F 评估 \u002F 原型、嵌入应用、自动化脚本。不适合：GUI 偏好用户（用 LM Studio）、多用户并发生产服务（用 vLLM）、模型浏览 \u002F 调参界面（用 LM Studio）。",[20,516,38],{"id":38},[40,518,519,525,534,540,547,562,568,574,580],{},[43,520,521,524],{},[29,522,523],{},"后台 Daemon","：开机自启，应用调用零延迟",[43,526,527,530,531],{},[29,528,529],{},"CLI","：",[212,532,533],{},"ollama pull \u002F run \u002F list \u002F show \u002F create \u002F serve",[43,535,536,539],{},[29,537,538],{},"Modelfile","：类 Dockerfile 注册任意 GGUF，配 SYSTEM \u002F PARAMETER \u002F TEMPLATE",[43,541,542,530,544],{},[29,543,71],{},[212,545,546],{},"http:\u002F\u002Flocalhost:11434\u002Fv1\u002Fchat\u002Fcompletions",[43,548,549,530,552,555,556,555,559],{},[29,550,551],{},"原生 API",[212,553,554],{},"\u002Fapi\u002Fchat","、",[212,557,558],{},"\u002Fapi\u002Fgenerate",[212,560,561],{},"\u002Fapi\u002Fembeddings",[43,563,564,567],{},[29,565,566],{},"模型库","：官方注册表内置 Llama \u002F Qwen \u002F DeepSeek \u002F Gemma \u002F Mistral \u002F GPT-OSS 等",[43,569,570,573],{},[29,571,572],{},"MLX 加速（Mac）","：0.19+ 起 M 系列自动用 MLX",[43,575,576,579],{},[29,577,578],{},"量化","：默认 Q4_K_M、支持 Q5 \u002F Q8 \u002F FP16",[43,581,582,585],{},[29,583,584],{},"跨平台","：Win \u002F Mac \u002F Linux 安装包，Docker 官方镜像",[20,587,93],{"id":93},[25,589,590],{},"完全免费、MIT 开源、商用免费。",[20,592,594],{"id":593},"实测m2-pro-qwen3-coder-7b-q4","实测（M2 Pro + Qwen3-Coder-7B Q4）",[25,596,597],{},[29,598,147],{},[40,600,601,607,610,613,616],{},[43,602,603,606],{},[212,604,605],{},"ollama run qwen3-coder:7b"," 一行起飞，3 秒进交互",[43,608,609],{},"REST API 配 Cursor \u002F Cline \u002F Continue 几乎全工具开箱即用",[43,611,612],{},"Modelfile 写自定义编码助手（low temperature + system prompt + 16K context）几分钟搞定",[43,614,615],{},"多模型并存，按需切换，内存占用合理",[43,617,618],{},"Mac M 系列 MLX 后比旧 GGUF 模式快显著",[25,620,621],{},[29,622,169],{},[40,624,625,635,641,648,651],{},[43,626,627,628,631,632],{},"默认 ",[212,629,630],{},"num_ctx"," 偏小（2048），跑长上下文要在 Modelfile 加 ",[212,633,634],{},"PARAMETER num_ctx 16384",[43,636,637,638],{},"模型默认走 0.0.0.0:11434 ↔ Docker 容器互访要 ",[212,639,640],{},"--add-host=host.docker.internal:host-gateway",[43,642,643,644,647],{},"国内 ",[212,645,646],{},"ollama.com\u002Flibrary"," 下载偶有慢，可手动 HF 下 GGUF + Modelfile 自建",[43,649,650],{},"多用户并发吞吐显著低于 vLLM",[43,652,653],{},"没有 GUI，模型浏览 \u002F 参数面板要走 LM Studio \u002F Open WebUI 配合",[20,655,189],{"id":189},[191,657,658,664,670,675,681,687],{},[43,659,660,663],{},[212,661,662],{},"curl -fsSL https:\u002F\u002Follama.ai\u002Finstall.sh | sh","（Mac \u002F Linux）；Windows winget",[43,665,666,669],{},[212,667,668],{},"ollama pull qwen3-coder:7b","（按需换模型）",[43,671,672,674],{},[212,673,605],{}," 直接聊",[43,676,677,678],{},"应用接入：baseURL = ",[212,679,680],{},"http:\u002F\u002Flocalhost:11434\u002Fv1",[43,682,683,684],{},"自定义：写 Modelfile → ",[212,685,686],{},"ollama create my-coder -f Modelfile",[43,688,689],{},"进阶：装 Open WebUI 做前端 \u002F 多人共享",[20,691,217],{"id":217},[101,693,694,709],{},[104,695,696],{},[107,697,698,700,702,704,706],{},[110,699,226],{},[110,701,231],{},[110,703,234],{},[110,705,414],{},[110,707,708],{},"llama.cpp",[119,710,711,728,743,758,773,789,805],{},[107,712,713,716,719,722,725],{},[124,714,715],{},"形态",[124,717,718],{},"CLI + Daemon",[124,720,721],{},"GUI + Headless",[124,723,724],{},"Python Server",[124,726,727],{},"C++ 二进制",[107,729,730,732,735,737,740],{},[124,731,189],{},[124,733,734],{},"极低",[124,736,734],{},[124,738,739],{},"中",[124,741,742],{},"高",[107,744,745,748,750,753,756],{},[124,746,747],{},"模型浏览",[124,749,529],{},[124,751,752],{},"✅ GUI",[124,754,755],{},"无",[124,757,755],{},[107,759,760,763,766,769,771],{},[124,761,762],{},"OpenAI 兼容",[124,764,765],{},"✅ :11434",[124,767,768],{},"✅ :1234",[124,770,246],{},[124,772,246],{},[107,774,775,778,781,784,787],{},[124,776,777],{},"多用户吞吐",[124,779,780],{},"弱（~40 tok\u002Fs）",[124,782,783],{},"中（50–90）",[124,785,786],{},"强（800–12500）",[124,788,739],{},[107,790,791,794,797,799,802],{},[124,792,793],{},"MLX (Mac)",[124,795,796],{},"✅ 0.19+",[124,798,246],{},[124,800,801],{},"部分",[124,803,804],{},"–",[107,806,807,809,811,813,816],{},[124,808,307],{},[124,810,310],{},[124,812,315],{},[124,814,815],{},"Apache 2.0",[124,817,310],{},[20,819,318],{"id":318},[40,821,822,828,834,840,846],{},[43,823,824,827],{},[29,825,826],{},"num_ctx 一定要设","：默认 2K 太小，跑代码 \u002F 长文档要 16K+",[43,829,830,833],{},[29,831,832],{},"Modelfile 模板别漏 TEMPLATE","：错的 chat template 会让模型输出乱码 \u002F 不停",[43,835,836,839],{},[29,837,838],{},"KV cache 爆表 = 速度悬崖","：32B 模型 32K 上下文，KV cache 可能 12+ GB，超显存自动 offload 慢 10×",[43,841,842,845],{},[29,843,844],{},"不要 0.0.0.0 直接对公网","：默认无鉴权，对外暴露走反代 + Bearer \u002F mTLS",[43,847,848,851],{},[29,849,850],{},"Mac 让它自动用 MLX","：升 0.19+；不要手动强制 GGUF + Metal",[20,853,354],{"id":353},[40,855,856,859,862,865,868,871,874],{},[43,857,858],{},"✅ 应用 \u002F IDE 接本地模型（Cursor \u002F Cline \u002F Continue）",[43,860,861],{},"✅ 个人 \u002F 评估 \u002F 脚本自动化",[43,863,864],{},"✅ Modelfile 自定义系统 prompt + 参数",[43,866,867],{},"✅ Mac M 系列 MLX 用户",[43,869,870],{},"❌ 多用户并发生产服务（用 vLLM）",[43,872,873],{},"❌ GUI 调参 \u002F 模型浏览（配 LM Studio \u002F Open WebUI）",[43,875,876],{},"❌ 极致单卡吞吐研究（直接 llama.cpp \u002F vLLM）",[20,878,402],{"id":402},[40,880,881,887,893,899],{},[43,882,883],{},[406,884,886],{"href":885},"\u002Ftools\u002Fcoding\u002Flocal\u002Flm-studio","LM Studio 评测",[43,888,889],{},[406,890,892],{"href":891},"\u002Ftools\u002Fcoding\u002Flocal\u002Fopen-webui","Open WebUI 评测",[43,894,895],{},[406,896,898],{"href":897},"\u002Ftools\u002Fcoding\u002Flocal\u002Fcherry-studio","Cherry Studio 评测",[43,900,901],{},[406,902,904],{"href":903},"\u002Fplaybook\u002Fonboarding\u002Frag-pipeline-build","RAG Pipeline 搭建 Playbook",[20,906,421],{"id":421},[191,908,909,916,923],{},[43,910,911,912],{},"Markaicode — Import GGUF Models into Ollama 2026（2026-05-15）",[406,913,914],{"href":914,"rel":915},"https:\u002F\u002Fmarkaicode.com\u002Fimport-gguf-models-ollama-guide",[435],[43,917,918,919],{},"ComputingForGeeks — Ollama Models Cheat Sheet 2026 ",[406,920,921],{"href":921,"rel":922},"https:\u002F\u002Fcomputingforgeeks.com\u002Follama-models-cheat-sheet",[435],[43,924,925,926],{},"Codersera — Ollama vs LM Studio vs vLLM vs llama.cpp vs MLX 2026 ",[406,927,928],{"href":928,"rel":929},"https:\u002F\u002Fcodersera.com\u002Fblog\u002Follama-vs-lm-studio-vs-vllm-vs-llama-cpp-vs-mlx-2026\u002F",[435],{"title":445,"searchDepth":446,"depth":446,"links":931},[932,933,934,935,936,937,938,939,940,941],{"id":22,"depth":449,"text":23},{"id":38,"depth":449,"text":38},{"id":93,"depth":449,"text":93},{"id":593,"depth":449,"text":594},{"id":189,"depth":449,"text":189},{"id":217,"depth":449,"text":217},{"id":318,"depth":449,"text":318},{"id":353,"depth":449,"text":354},{"id":402,"depth":449,"text":402},{"id":421,"depth":449,"text":421},"\u002Fimg\u002Ftools\u002Follama.webp","Ollama 真实评测：本地 LLM 的事实标准 Daemon，CLI + REST API，模型库 + Modelfile + GGUF 一站式。0.19+ 在 Mac M 系列用 MLX 加速；OpenAI 兼容端点 11434；MIT 开源 + 跨平台。",[945,948,951,954],{"q":946,"a":947},"和 LM Studio 怎么选？","Ollama = Daemon + CLI，开机自启在 11434 端口跑，应用 \u002F IDE 调它最方便。LM Studio = GUI，模型浏览 \u002F 调参 \u002F 聊天体验更好。两者底层都基于 llama.cpp，Mac M 系列上都已切 MLX。",{"q":949,"a":950},"Modelfile 是什么？","类 Dockerfile 的模型配置：`FROM .\u002Fxxx.gguf` + PARAMETER \u002F TEMPLATE \u002F SYSTEM。把任意 GGUF 注册成本地模型供调用。`ollama create my-model -f Modelfile`。",{"q":952,"a":953},"OpenAI 兼容端点？","`http:\u002F\u002Flocalhost:11434\u002Fv1`。任何 OpenAI SDK 改 baseURL 即用。也可走原生 `\u002Fapi\u002Fchat`、`\u002Fapi\u002Fgenerate`。",{"q":955,"a":956},"并发能力？","单用户原型场景顺滑（~40 tok\u002Fs peak），多用户并发明显不如 vLLM（vLLM 的 PagedAttention + 连续批处理高 16–20×）。生产并发选 vLLM。",[466],{},"\u002Ftools\u002Fcoding\u002Flocal\u002Follama",[473,474,475,961],"docker",[963],{"plan":126,"price":964,"features":965,"notes":966},"免费","完整 CLI + REST API + Modelfile + 模型库 + MIT 协议","全平台、商用免费","完全免费 + 开源（MIT）","2026-06-19",[970,971],"onboarding\u002Frag-pipeline-build","onboarding\u002Fclaude-code-getting-started",{"power":479,"ux":479,"price":480,"cn_support":446,"stability":480},{"title":231,"description":943},"Ollama 评测 2026：本地运行大模型，开源 AI 模型管理工具，私有化部署指南",[976,979,981],{"name":977,"url":914,"accessed":978},"Markaicode — Import GGUF 2026","2026-06-24",{"name":980,"url":921,"accessed":978},"ComputingForGeeks — Ollama Cheat Sheet 2026",{"name":982,"url":928,"accessed":978},"Codersera — Ollama vs LM Studio vs vLLM 2026","tools\u002Fcoding\u002Flocal\u002Follama","本地 LLM 的 Daemon——CLI + REST API 后台跑，给 Cursor \u002F Cline \u002F Open WebUI 接本地模型最低门槛",[460,986,987,988,989,492,990,991,992],"daemon","cli","rest-api","modelfile","mlx","openai-compatible","open-source","本地 LLM 的 Daemon 事实标准，CLI \u002F Modelfile \u002F REST API 三件套配合最广泛。GUI 偏好用户走 LM Studio；多用户并发生产用 vLLM；其他场景几乎默认 Ollama。","https:\u002F\u002Follama.com","7WgXNX9uMzSH_c-dUkicVopZk_g1z8HaB_8FmD9fBps",1785428443658]