{
  "source_file": "0930",
  "source_platform": "Ghost",
  "author": "Avi Chawla / Daily Dose of Data Science",
  "title_listed": "4 Ways To Run LLMs Locally",
  "keywords": "",
  "domain": "大模型算法",
  "content_type": "深度技术解析",
  "is_paid_flag": "否",
  "url": "https://www.dailydoseofds.com/p/4-ways-to-run-llms-locally/",
  "publish_date": "2026-06-02",
  "corpus_stage": "",
  "notes": "",
  "id": "08e7ecc56065",
  "collected_at": "2026-10-02T13:47:19",
  "title": "4 Ways to Run LLMs Locally",
  "body_markdown": "Feb 10, 2025\nLLMs\n4 Ways to Run LLMs Locally\nLlama-3, DeepSeek, Phi, and many many more.\nAvi Chawla\n👉\nBeing able to run LLMs also has many upsides:\nPrivacy since your data never leaves your machine.\nTesting things locally before moving to the cloud and more.\nHere are four ways to run LLMs locally.\n#1) Ollama\nRunning a model through Ollama is as simple as executing this command:\nTo get started, install Ollama with a single command:\nDone!\nNow, you can download any of the\nsupported models\nusing these commands:\nFor programmatic usage, you can also install the Python package of Ollama or its integration with orchestration frameworks like Llama Index or CrewAI:\nWe heavily used Ollama in our\nRAG crash course\nif you want to dive deeper.\nThe video below shows the usage of\nollama run deepseek-r1\ncommand:\n0:00\n/\n0:20\n1×\n#2) LMStudio\nLMStudio can be installed as an app on your computer.\nThe app does not collect data or monitor your actions. Your data stays local on your machine. It’s free for personal use.\nIt offers a ChatGPT-like interface, allowing you to load and eject models as you chat. This video shows its usage:\n0:00\n/\n1:59\n1×\nJust like Ollama,\nLMStudio supports several LLMs\nas well.\n#3) vLLM\nvLLM is a fast and easy-to-use library for LLM inference and serving.\nWith just a few lines of code, you can locally run LLMs (like DeepSeek) in an OpenAI-compatible format:\n#4) LlamaCPP\nLlamaCPP enables LLM inference with minimal setup and good performance.\nHere’s DeepSeek-R1 running on a Mac Studio:\n0:00\n/\n1:59\n1×\nAnd these were four ways to run LLMs locally on your computer.\nIf you don’t want to get into the hassle of local setups,\n​\nSambaNova\n’s fastest inference can be integrated into your existing LLM apps in just three lines of code:\nAlso, if you want to dive into building LLM apps, our full RAG crash course discusses RAG from basics to beyond:\nRAG fundamentals\nRAG evaluation\nRAG optimization\nMultimodal RAG\nGraph RAG\nMultivector retrieval using ColBERT\nRAG over complex real-world docs ft. ColPali\n👉 Over to you: Which method do you find the most useful?\nThanks for reading!\nPublished on Feb 10, 2025\nComments\nShare\nCopy link\nShare to X\nShare to Facebook\nShare to Linkedin\nCopied\nPrevious\nAgentic Systems 101: Fundamentals, Building Blocks, and How to Build Them (Part A)\nNext\nAgentic Systems 101: Fundamentals, Building Blocks, and How to Build Them (Part B)",
  "metadata": {
    "title": "4 Ways to Run LLMs Locally",
    "description": "Llama-3, DeepSeek, Phi, and many many more.",
    "keywords": null,
    "author": null,
    "og:site_name": "Daily Dose of Data Science",
    "og:type": "article",
    "og:title": "4 Ways to Run LLMs Locally",
    "og:description": "Llama-3, DeepSeek, Phi, and many many more.",
    "og:url": "https://www.dailydoseofds.com/p/4-ways-to-run-llms-locally/",
    "og:image": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/size/w1200/2025/02/f8f45beb-780a-45b0-9798-b7c62eee446e_2488x1196.png",
    "og:image:width": "1200",
    "og:image:height": "577",
    "twitter:card": "summary_large_image",
    "twitter:title": "4 Ways to Run LLMs Locally",
    "twitter:description": "Llama-3, DeepSeek, Phi, and many many more.",
    "twitter:url": "https://www.dailydoseofds.com/p/4-ways-to-run-llms-locally/",
    "twitter:image": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/size/w1200/2025/02/f8f45beb-780a-45b0-9798-b7c62eee446e_2488x1196.png",
    "twitter:label1": "Written by",
    "twitter:data1": "Avi Chawla",
    "twitter:label2": "Filed under",
    "twitter:data2": "LLMs",
    "twitter:site": "@_avichawla",
    "article:published_time": "2025-02-09T19:04:00.000Z",
    "article:modified_time": "2026-06-02T21:19:18.000Z",
    "article:tag": "LLMs"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [],
  "images": [
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/size/w400/2026/03/avi-google.jpg",
      "bytes": 11344,
      "reused": true,
      "local_path": "attachments/08e7ecc56065/images/000.jpg",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/size/w400/2026/03/avi-google.jpg",
      "alt": "Avi Chawla",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f4b04a74c-ee54-42b1-b306-1bbc14f434d0_1648x676-1.png",
      "bytes": 75785,
      "reused": true,
      "local_path": "attachments/08e7ecc56065/images/001.png",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f4b04a74c-ee54-42b1-b306-1bbc14f434d0_1648x676-1.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f18c32fea-4ddb-41ca-bc0d-e0a0e11a532b_2376x676-1.png",
      "bytes": 47360,
      "reused": true,
      "local_path": "attachments/08e7ecc56065/images/004.png",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f18c32fea-4ddb-41ca-bc0d-e0a0e11a532b_2376x676-1.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2ff8f45beb-780a-45b0-9798-b7c62eee446e_2488x1196-1.png",
      "bytes": 115869,
      "reused": true,
      "local_path": "attachments/08e7ecc56065/images/007.png",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2ff8f45beb-780a-45b0-9798-b7c62eee446e_2488x1196-1.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f5bc933c7-44e0-401d-8b22-98d5e8850057_2456x892-1.png",
      "bytes": 57215,
      "reused": true,
      "local_path": "attachments/08e7ecc56065/images/010.png",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f5bc933c7-44e0-401d-8b22-98d5e8850057_2456x892-1.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f76ec243f-d748-4012-a7ca-2b5f9428a25f_1528x1628-1.png",
      "bytes": 379108,
      "reused": true,
      "local_path": "attachments/08e7ecc56065/images/013.png",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f76ec243f-d748-4012-a7ca-2b5f9428a25f_1528x1628-1.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f8df859a1-feac-40be-a5c6-8d11a279f6de_1640x1140-1.png",
      "bytes": 212651,
      "reused": true,
      "local_path": "attachments/08e7ecc56065/images/016.png",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f8df859a1-feac-40be-a5c6-8d11a279f6de_1640x1140-1.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f6251ef7f-6228-4996-ab27-3b3a8ab55e25_1456x631-1.png",
      "bytes": 43203,
      "reused": true,
      "local_path": "attachments/08e7ecc56065/images/019.png",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/2026/01/https-3a-2f-2fsubstack-post-media-s3-amazonaws-com-2fpublic-2fimages-2f6251ef7f-6228-4996-ab27-3b3a8ab55e25_1456x631-1.png",
      "alt": "",
      "downloaded": true
    }
  ],
  "audio": [],
  "videos": [
    {
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/Psuy_TX7AWGpCeTN.mp4",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/Psuy_TX7AWGpCeTN.mp4",
      "status": "invalid_or_wrong_resolution",
      "kind": "direct_video",
      "bytes": 801940,
      "reused": true,
      "content_type": "application/octet-stream",
      "valid": true,
      "height": 360,
      "width": 564,
      "duration": "20.283333",
      "local_path": "attachments/08e7ecc56065/videos/repair-4ddec320ce81b7b5c30b.mp4",
      "title": "",
      "retried_at": "2026-10-20T17:55:04Z"
    },
    {
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/lmstudio.mp4",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/lmstudio.mp4",
      "status": "ok",
      "kind": "direct_video",
      "bytes": 6623464,
      "reused": false,
      "content_type": "application/octet-stream",
      "valid": true,
      "height": 720,
      "width": 1280,
      "duration": "119.845500",
      "local_path": "attachments/08e7ecc56065/videos/repair-a3a719251ce519664a54.mp4"
    },
    {
      "url": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/lmstudio-1.mp4",
      "src": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/lmstudio-1.mp4",
      "status": "ok",
      "kind": "direct_video",
      "bytes": 6623464,
      "reused": false,
      "content_type": "application/octet-stream",
      "valid": true,
      "height": 720,
      "width": 1280,
      "duration": "119.845500",
      "local_path": "attachments/08e7ecc56065/videos/repair-1a6a7afb18569ec2850a.mp4"
    }
  ],
  "links": [
    {
      "href": "https://ollama.com/search?ref=dailydoseofds.com",
      "label": "supported models",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/a-crash-course-on-building-rag-systems-part-1-with-implementations/",
      "label": "RAG crash course",
      "type": "a"
    },
    {
      "href": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/Psuy_TX7AWGpCeTN.mp4",
      "label": "",
      "type": "video"
    },
    {
      "href": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/lmstudio.mp4",
      "label": "",
      "type": "video"
    },
    {
      "href": "https://lmstudio.ai/models?ref=dailydoseofds.com",
      "label": "LMStudio supports several LLMs",
      "type": "a"
    },
    {
      "href": "https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/media/2025/02/lmstudio-1.mp4",
      "label": "",
      "type": "video"
    },
    {
      "href": "https://fnf.dev/3WKd1B9?ref=dailydoseofds.com",
      "label": "​",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/a-crash-course-on-building-rag-systems-part-2-with-implementations/",
      "label": "RAG evaluation",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/a-crash-course-on-building-rag-systems-part-3-with-implementation/",
      "label": "RAG optimization",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/a-crash-course-on-building-rag-systems-part-5-with-implementation/",
      "label": "Multimodal RAG",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/a-crash-course-on-building-rag-systems-part-7-with-implementation/",
      "label": "Graph RAG",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/a-crash-course-on-building-rag-systems-part-8-with-implementation/",
      "label": "Multivector retrieval using ColBERT",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/a-crash-course-on-building-rag-systems-part-9-with-implementation/",
      "label": "RAG over complex real-world docs ft. ColPali",
      "type": "a"
    },
    {
      "href": "https://x.com/intent/tweet?url=https%3A%2F%2Fwww.dailydoseofds.com%2Fp%2F4-ways-to-run-llms-locally%2F&text=4%20Ways%20to%20Run%20LLMs%20Locally",
      "label": "Share to X",
      "type": "a"
    },
    {
      "href": "https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fwww.dailydoseofds.com%2Fp%2F4-ways-to-run-llms-locally%2F",
      "label": "Share to Facebook",
      "type": "a"
    },
    {
      "href": "https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fwww.dailydoseofds.com%2Fp%2F4-ways-to-run-llms-locally%2F",
      "label": "Share to Linkedin",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/ai-agents-crash-course-part-1-with-implementation/",
      "label": "Previous Agentic Systems 101: Fundamentals, Building Blocks, and How to Build Them (Part A)",
      "type": "a"
    },
    {
      "href": "https://www.dailydoseofds.com/ai-agents-crash-course-part-2-with-implementation/",
      "label": "Next Agentic Systems 101: Fundamentals, Building Blocks, and How to Build Them (Part B)",
      "type": "a"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:47:58Z",
  "source_url": "https://www.dailydoseofds.com/p/4-ways-to-run-llms-locally/",
  "papers": [],
  "actual_video_files": [],
  "body_chars": 2383,
  "expected_body_images": 8,
  "discovery_status": "ok",
  "delivery_status": "partial",
  "missing_reason": "invalid_or_wrong_resolution",
  "raw_html": "attachments/08e7ecc56065/pages/source.html",
  "local_html": "attachments/08e7ecc56065/pages/article.html",
  "body_base_path": "attachments/08e7ecc56065/pages/",
  "body_markdown_path": "attachments/08e7ecc56065/pages/article.md"
}