{"id":5622,"date":"2025-11-04T12:40:46","date_gmt":"2025-11-04T11:40:46","guid":{"rendered":"https:\/\/kairntech.com\/doc\/?page_id=5622"},"modified":"2026-03-11T11:49:40","modified_gmt":"2026-03-11T10:49:40","slug":"hardware-recommandation","status":"publish","type":"page","link":"https:\/\/kairntech.com\/doc\/hardware-recommandation\/","title":{"rendered":"Hardware Recommandations"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\" id=\"general-hardware-recommendations-cpu\">Kairntech platform &#8211; no GPU<\/h2>\n\n\n\n<p>All engines and vectorizers are supported, with the exception of Transformers, BGE-M3 vectorizer\u2026<\/p>\n\n\n\n<figure class=\"wp-block-table is-style-regular\"><table class=\"has-black-color has-cyan-bluish-gray-background-color has-text-color has-background has-link-color has-fixed-layout\"><thead><tr><th><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\">Component<\/mark><\/th><th><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\">Specifications<\/mark><\/th><\/tr><\/thead><tbody><tr><td><strong><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\">CPU<\/mark><\/strong><\/td><td><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\"><strong>At least 8 cores<\/strong>, preferably more<br><strong>Base clock speed \u2265 3.0 GHz<\/strong><br><strong>Single Thread Rating (STR) Index \u2265 2200<\/strong><br>High <strong>core count<\/strong> is prioritized over single-thread speed<\/mark><\/td><\/tr><tr><td><strong><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\">RAM<\/mark><\/strong><\/td><td><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\">64 GB<\/mark><\/td><\/tr><tr><td><strong><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\">Disk<\/mark><\/strong><\/td><td><mark style=\"background-color:rgba(0, 0, 0, 0)\" class=\"has-inline-color has-black-color\">400 GB SSD with <strong>high read IOPS<\/strong> (\u2265 10,000)<\/mark><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Refer to <a href=\"https:\/\/www.cpubenchmark.net\/singleThread.html#server-thread\" target=\"_blank\" rel=\"noreferrer noopener\">CPU Benchmark<\/a> for reference.<\/p>\n\n\n\n<p><strong>Example<\/strong>:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<ul class=\"wp-block-list\">\n<li><strong>CPU<\/strong>: AMD Ryzen 7 7700X (8 cores \/ 16 threads, STR index: 4185, clock speed: 5.4 GHz)<\/li>\n\n\n\n<li><strong>RAM<\/strong>: 64 GB<\/li>\n\n\n\n<li><strong>SSD<\/strong>: Samsung 980 Pro 500 GB (PCIe 4.0 NVMe, high IOPS: 690&nbsp;000 read \/ 620&nbsp;000 write)<\/li>\n<\/ul>\n<\/blockquote>\n\n\n\n<div style=\"height:31px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"general-hardware-recommendations-cpu\">Kairntech platform &#8211; with GPU (recommended)<\/h2>\n\n\n\n<p>All engines and vectorizers supported. Training and inference times can be significantly reduced.<\/p>\n\n\n\n<figure class=\"wp-block-table is-style-regular\"><table class=\"has-cyan-bluish-gray-background-color has-background has-fixed-layout\"><thead><tr><th>Component<\/th><th>Specifications<\/th><\/tr><\/thead><tbody><tr><td><strong>CPU<\/strong><\/td><td><strong>At least 8 cores<\/strong>, preferably more<br><strong>Base clock speed \u2265 3.0 GHz<\/strong><br><strong>Single Thread Rating (STR) Index \u2265 2200<\/strong><br>High <strong>core count<\/strong> is prioritized over single-thread speed<\/td><\/tr><tr><td><strong>GPU \/ VRAM<\/strong><\/td><td><strong>\u2265 8 GB VRAM<\/strong><br>CUDA compute capability \u2265 7.5<\/td><\/tr><tr><td><strong>RAM<\/strong><\/td><td>64 GB, 128 GB recommended<\/td><\/tr><tr><td><strong>Disk<\/strong><\/td><td>400 GB SSD with <strong>high read IOPS<\/strong> (\u2265 10,000)<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Refer to <a href=\"https:\/\/www.cpubenchmark.net\/singleThread.html#server-thread\" target=\"_blank\" rel=\"noreferrer noopener\">CPU Benchmark<\/a> for reference.<\/p>\n\n\n\n<p><strong>Example<\/strong>:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<ul class=\"wp-block-list\">\n<li><strong>CPU<\/strong>: AMD Ryzen 7 9800X3D (8 cores \/ 16 threads, STR index: 4427, clock speed: 5.2 GHz)<\/li>\n\n\n\n<li><strong>GPU\/VRAM:<\/strong> NVIDIA RTX 3060 (12 GB VRAM)<\/li>\n\n\n\n<li><strong>RAM<\/strong>: 128 GB<\/li>\n\n\n\n<li><strong>SSD<\/strong>: Samsung 980 Pro 500 GB (PCIe 4.0 NVMe, high IOPS: 690&nbsp;000 read \/ 620&nbsp;000 write)<\/li>\n<\/ul>\n<\/blockquote>\n\n\n\n<div style=\"height:36px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"hardware-recommendation-for-local-llm-Inference-server-gpu\">Local LLM inference server (GPU required)<\/h2>\n\n\n\n<p>The goal is to run an LLM locally to ensure data privacy, maintain full control, and reduce long-term costs by moving AI operations from the cloud to your own hardware.<\/p>\n\n\n\n<figure class=\"wp-block-table is-style-regular\"><table class=\"has-cyan-bluish-gray-background-color has-background has-fixed-layout\"><thead><tr><th>Component<\/th><th>Specifications<\/th><\/tr><\/thead><tbody><tr><td><strong>CPU<\/strong><\/td><td><strong>At least 16 cores<\/strong>, preferably more<br><strong>Base clock speed \u2265 3.0 GHz<\/strong><br><strong>Single Thread Rating (STR) Index \u2265 2000<\/strong><\/td><\/tr><tr><td><strong>GPU \/ VRAM<\/strong><\/td><td>\u2265 <strong>48 GB<\/strong> <strong>VRAM<\/strong> (<strong>16 GB VRAM<\/strong> with quantized models)<br>to run GPT-OSS-20B, Mistral 24B&#8230;<\/td><\/tr><tr><td><strong>RAM<\/strong><\/td><td><strong>128 GB<\/strong><\/td><\/tr><tr><td><strong>Disk<\/strong><\/td><td>2 TB NVMe SSD (PCIe Gen4)<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Refer to <a href=\"https:\/\/www.cpubenchmark.net\/singleThread.html#server-thread\" target=\"_blank\" rel=\"noreferrer noopener\">CPU Benchmark<\/a> for reference.<\/p>\n\n\n\n<p><strong>Example<\/strong>:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<ul class=\"wp-block-list\">\n<li><strong>CPU<\/strong>: AMD Threadripper 7970X (32 cores \/ 64 threads, STR index: 4170, clock speed: 5.3 GHz)<\/li>\n\n\n\n<li><strong>GPU\/VRAM:<\/strong> NVIDIA RTX 6000 ada (48 GB VRAM)<\/li>\n\n\n\n<li><strong>RAM<\/strong>: 128 GB<\/li>\n\n\n\n<li><strong>SSD<\/strong>: Samsung 980 Pro 2 TB (PCIe 4.0 NVMe, high IOPS: 690&nbsp;000 read \/ 660&nbsp;000 write)<\/li>\n<\/ul>\n<\/blockquote>\n\n\n\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"general-hardware-recommendations-cpu\">Entity-fishing server (no GPU required)<\/h2>\n\n\n\n<p>The entity-fishing server aims to automatically annotate content using Wikidata and the Wikipedia knowledge base. It is mainly combined with a NER model within a pipeline.<\/p>\n\n\n\n<figure class=\"wp-block-table is-style-regular\"><table class=\"has-cyan-bluish-gray-background-color has-background has-fixed-layout\"><thead><tr><th>Component<\/th><th>Specifications<\/th><\/tr><\/thead><tbody><tr><td><strong>CPU<\/strong><\/td><td>8 physical cores, CPUs with <strong>high sustained all-core turbo frequencies<\/strong>, ideally &gt; <strong>3 GHz<\/strong><\/td><\/tr><tr><td><strong>RAM<\/strong><\/td><td>128 GB recommended<\/td><\/tr><tr><td><strong>Disk<\/strong><\/td><td>400 GB SSD with <strong>high read IOPS<\/strong> (\u2265 10,000)<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Refer to <a href=\"https:\/\/www.cpubenchmark.net\/singleThread.html#server-thread\" target=\"_blank\" rel=\"noreferrer noopener\">CPU Benchmark<\/a> for reference.<\/p>\n\n\n\n<p><strong>Example<\/strong>:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<ul class=\"wp-block-list\">\n<li><strong>CPU<\/strong>: AMD Ryzen 7 5700G (8 cores \/ 16 threads, STP index: 3273, clock speed: 4.6 GHz)<\/li>\n\n\n\n<li><strong>RAM<\/strong>: 128 GB<\/li>\n\n\n\n<li><strong>SSD<\/strong>: Samsung 980 Pro 1 TB (PCIe 4.0 NVMe, high IOPS: 690&nbsp;000 read \/ 660&nbsp;000 write)<\/li>\n\n\n\n<li><\/li>\n<\/ul>\n<\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Kairntech platform &#8211; no GPU All engines and vectorizers are supported, with the exception of Transformers, BGE-M3 vectorizer\u2026 Component Specifications CPU At least 8 cores, preferably moreBase clock speed \u2265 3.0 GHzSingle Thread Rating (STR) Index \u2265 2200High core count is prioritized over single-thread speed RAM 64 GB Disk 400 GB SSD with high read [&hellip;]<\/p>\n","protected":false},"author":6,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-5622","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Hardware Recommandations - Kairntech Documentation<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/kairntech.com\/doc\/hardware-recommandation\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Hardware Recommandations - Kairntech Documentation\" \/>\n<meta property=\"og:description\" content=\"Kairntech platform &#8211; no GPU All engines and vectorizers are supported, with the exception of Transformers, BGE-M3 vectorizer\u2026 Component Specifications CPU At least 8 cores, preferably moreBase clock speed \u2265 3.0 GHzSingle Thread Rating (STR) Index \u2265 2200High core count is prioritized over single-thread speed RAM 64 GB Disk 400 GB SSD with high read [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/kairntech.com\/doc\/hardware-recommandation\/\" \/>\n<meta property=\"og:site_name\" content=\"Kairntech Documentation\" \/>\n<meta property=\"article:modified_time\" content=\"2026-03-11T10:49:40+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/kairntech.com\/doc\/hardware-recommandation\/\",\"url\":\"https:\/\/kairntech.com\/doc\/hardware-recommandation\/\",\"name\":\"Hardware Recommandations - Kairntech Documentation\",\"isPartOf\":{\"@id\":\"https:\/\/kairntech.com\/doc\/#website\"},\"datePublished\":\"2025-11-04T11:40:46+00:00\",\"dateModified\":\"2026-03-11T10:49:40+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/kairntech.com\/doc\/hardware-recommandation\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/kairntech.com\/doc\/hardware-recommandation\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/kairntech.com\/doc\/hardware-recommandation\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/kairntech.com\/doc\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Hardware Recommandations\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/kairntech.com\/doc\/#website\",\"url\":\"https:\/\/kairntech.com\/doc\/\",\"name\":\"Kairntech Documentation\",\"description\":\"All the information you need to use Kairntech Software, methodology,  user and installation guides.\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/kairntech.com\/doc\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Hardware Recommandations - Kairntech Documentation","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/kairntech.com\/doc\/hardware-recommandation\/","og_locale":"en_GB","og_type":"article","og_title":"Hardware Recommandations - Kairntech Documentation","og_description":"Kairntech platform &#8211; no GPU All engines and vectorizers are supported, with the exception of Transformers, BGE-M3 vectorizer\u2026 Component Specifications CPU At least 8 cores, preferably moreBase clock speed \u2265 3.0 GHzSingle Thread Rating (STR) Index \u2265 2200High core count is prioritized over single-thread speed RAM 64 GB Disk 400 GB SSD with high read [&hellip;]","og_url":"https:\/\/kairntech.com\/doc\/hardware-recommandation\/","og_site_name":"Kairntech Documentation","article_modified_time":"2026-03-11T10:49:40+00:00","twitter_card":"summary_large_image","twitter_misc":{"Estimated reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/kairntech.com\/doc\/hardware-recommandation\/","url":"https:\/\/kairntech.com\/doc\/hardware-recommandation\/","name":"Hardware Recommandations - Kairntech Documentation","isPartOf":{"@id":"https:\/\/kairntech.com\/doc\/#website"},"datePublished":"2025-11-04T11:40:46+00:00","dateModified":"2026-03-11T10:49:40+00:00","breadcrumb":{"@id":"https:\/\/kairntech.com\/doc\/hardware-recommandation\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/kairntech.com\/doc\/hardware-recommandation\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/kairntech.com\/doc\/hardware-recommandation\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/kairntech.com\/doc\/"},{"@type":"ListItem","position":2,"name":"Hardware Recommandations"}]},{"@type":"WebSite","@id":"https:\/\/kairntech.com\/doc\/#website","url":"https:\/\/kairntech.com\/doc\/","name":"Kairntech Documentation","description":"All the information you need to use Kairntech Software, methodology,  user and installation guides.","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/kairntech.com\/doc\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"}]}},"jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/kairntech.com\/doc\/wp-json\/wp\/v2\/pages\/5622","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/kairntech.com\/doc\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/kairntech.com\/doc\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/kairntech.com\/doc\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/kairntech.com\/doc\/wp-json\/wp\/v2\/comments?post=5622"}],"version-history":[{"count":32,"href":"https:\/\/kairntech.com\/doc\/wp-json\/wp\/v2\/pages\/5622\/revisions"}],"predecessor-version":[{"id":5678,"href":"https:\/\/kairntech.com\/doc\/wp-json\/wp\/v2\/pages\/5622\/revisions\/5678"}],"wp:attachment":[{"href":"https:\/\/kairntech.com\/doc\/wp-json\/wp\/v2\/media?parent=5622"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}