{"id":6588,"date":"2026-06-21T22:59:16","date_gmt":"2026-06-21T17:59:16","guid":{"rendered":"https:\/\/cifrum.kz\/how-to-install-ollama-2026\/"},"modified":"2026-06-21T23:14:18","modified_gmt":"2026-06-21T18:14:18","slug":"how-to-install-ollama-2026","status":"publish","type":"post","link":"https:\/\/cifrum.kz\/en\/how-to-install-ollama-2026\/","title":{"rendered":"How to Install Ollama in 2026: Step-by-Step Guide"},"content":{"rendered":"\n<p class=\"has-large-font-size wp-block-paragraph\"><strong>Ollama allows you to run language models on your own computer<\/strong>: Requests to the local model are processed without sending text to a third-party cloud chat. In this instruction, we will install Ollama on macOS or Windows, launch the first model, check the API and, if desired, add the Open WebUI graphical interface.<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p><strong>Current as of June 21, 2026.<\/strong> Latest stable release &#8211; <a href=\"https:\/\/github.com\/ollama\/ollama\/releases\/tag\/v0.30.10\" target=\"_blank\" rel=\"noopener\">Ollama v0.30.10<\/a>, published June 17. The interface and commands may change in future versions.<\/p><\/blockquote>\n\n\n\n<h2 class=\"wp-block-heading\">What is Ollama and why is it needed?<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Ollama is a free tool for downloading and running open models locally. Its <a href=\"https:\/\/ollama.com\/models\" target=\"_blank\" rel=\"noopener\">official library<\/a> includes Qwen, Llama, DeepSeek, Gemma, Mistral, and other model families. Ollama manages model files, uses available GPU acceleration, and provides a local API at <code>http:\/\/localhost:11434<\/code>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">After loading the local model, the Internet is not needed for normal dialogue. However, it is required for installation, updates and downloading of models. In addition, Ollama has cloud models: if privacy is a concern, choose a local model tag and check where the request is being made.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">System requirements: how much memory will be needed<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The official documentation specifies operating system and GPU compatibility requirements, but does not specify a universal RAM or VRAM minimum. Memory consumption depends on model size, quantization, and context length. Therefore, the table below is a practical guide and not a guarantee of performance.<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table><thead><tr><th>Configuration<\/th><th>Where to start<\/th><th>Comment<\/th><\/tr><\/thead><tbody><tr><td>8 GB RAM<\/td><td><code>llama3.2:1b<\/code> or <code>llama3.2:3b<\/code><\/td><td>Suitable for learning the basics; close memory-heavy apps<\/td><\/tr><tr><td>16 GB RAM \/ unified memory<\/td><td><code>qwen3:4b<\/code>, sometimes <code>qwen3:8b<\/code><\/td><td>A practical minimum for compact models<\/td><\/tr><tr><td>32 GB<\/td><td>8B\u201314B models<\/td><td>More headroom for context and other running apps<\/td><\/tr><tr><td>32\u201364 GB or more<\/td><td><code>qwen3:30b<\/code>, <code>qwen3-coder:30b<\/code><\/td><td>The model file is about 19 GB, but additional memory is required<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<ul class=\"wp-block-list\"><li><strong>macOS:<\/strong> Requires macOS Sonoma 14 or later. Apple Silicon uses the GPU through Metal and shared memory; Intel Mac is supported in CPU mode.<\/li><li><strong>Windows:<\/strong> Requires Windows 10 22H2 or later. The installer works without administrator rights.<\/li><li><strong>NVIDIA:<\/strong> By <a href=\"https:\/\/docs.ollama.com\/gpu\" target=\"_blank\" rel=\"noopener\">official compatibility list<\/a> You need compute capability 5.0+ and an up-to-date driver; for new versions, the documentation indicates driver 531+.<\/li><li><strong>Disk:<\/strong> A Windows installation requires at least 4 GB, and models take up from hundreds of megabytes to tens and hundreds of gigabytes.<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Step 1: Install Ollama on macOS<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The clearest way is to open <a href=\"https:\/\/ollama.com\/download\/mac\" target=\"_blank\" rel=\"noopener\">official download page<\/a>, download <code>Ollama.dmg<\/code>, move the application to the Applications folder and run it. When you launch it for the first time, Ollama will prompt you to add the command <code>ollama<\/code> to the system <code>PATH<\/code>.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/cifrum.kz\/wp-content\/uploads\/2026\/06\/ollama-install-macos-en.png\" alt=\"Ways to install Ollama on macOS and verify the version in Terminal\"\/><figcaption class=\"wp-element-caption\">The official DMG is the simplest way to install Ollama on macOS, while the Terminal command is convenient for developers.<\/figcaption><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">An alternative official method is to install with one command:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>curl -fsSL https:\/\/ollama.com\/install.sh | sh<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">Ollama is also available through Homebrew, but it is a third-party manager package. If you&#8217;re already using Homebrew:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>brew install ollama<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">After installation, close and reopen Terminal, then check the version:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>ollama --version<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">Step 2: Install Ollama on Windows<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">On Windows, download <code>OllamaSetup.exe<\/code> from the <a href=\"https:\/\/ollama.com\/download\/windows\" target=\"_blank\" rel=\"noopener\">official page<\/a>. In the v0.30.10 release, the installer is about 1.3 GB. It does not require administrator rights and installs in the user&#8217;s home directory by default.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/cifrum.kz\/wp-content\/uploads\/2026\/06\/ollama-install-windows-en.png\" alt=\"Installing Ollama on Windows with the installer or PowerShell\"\/><figcaption class=\"wp-element-caption\">Install Ollama on Windows with OllamaSetup.exe or the official PowerShell command.<\/figcaption><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Official installation via PowerShell:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>irm https:\/\/ollama.com\/install.ps1 | iex<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">Once complete, open a new PowerShell window and run:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>ollama --version<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">How to transfer models to another drive<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">If there is little space on drive C, open \u201cChange environment variables for your account\u201d, create a variable <code>OLLAMA_MODELS<\/code> and indicate, for example, <code>D:\\OllamaModels<\/code>. After saving, close Ollama completely in the system tray and launch it again. This procedure is described in <a href=\"https:\/\/docs.ollama.com\/windows\" target=\"_blank\" rel=\"noopener\">Ollama documentation for Windows<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Installation on Linux<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">For most Linux systems, the official project offers the same installation script:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>curl -fsSL https:\/\/ollama.com\/install.sh | sh<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">After installation, check the service with the commands <code>ollama --version<\/code> And <code>systemctl status ollama<\/code>. For NVIDIA, AMD and experimental Vulkan, check the latest <a href=\"https:\/\/docs.ollama.com\/gpu\" target=\"_blank\" rel=\"noopener\">hardware support page<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Step 3. Download and run the first model<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The <code>ollama run<\/code> command downloads the model and then opens an interactive chat. On a computer with 8 GB RAM, start with the compact Llama 3.2:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>ollama run llama3.2:3b<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">With 16 GB of memory, try <code>qwen3:4b<\/code> first, then <code>qwen3:8b<\/code> if the system has enough headroom:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>ollama run qwen3:4b\nollama run qwen3:8b<\/code><\/pre>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/cifrum.kz\/wp-content\/uploads\/2026\/06\/ollama-model-selection-en.png\" alt=\"Comparison of local Ollama models by size and purpose\"\/><figcaption class=\"wp-element-caption\">Start with a small model and move to a larger one only when you have enough spare RAM or unified memory.<\/figcaption><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Enter a question after the prompt <code>&gt;&gt;&gt;<\/code>. To exit use <code>\/bye<\/code> or combination <code>Ctrl+D<\/code>. Useful commands:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>ollama list\nollama ps\nollama pull qwen3:8b\nollama rm qwen3:8b<\/code><\/pre>\n\n\n\n<ul class=\"wp-block-list\"><li><code>ollama list<\/code> \u2014 show downloaded models.<\/li><li><code>ollama ps<\/code> \u2014 show models loaded into memory.<\/li><li><code>ollama pull<\/code> \u2014 download or update the model.<\/li><li><code>ollama rm<\/code> \u2014 delete the model from the disk.<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Which models to choose in June 2026<\/h2>\n\n\n\n<figure class=\"wp-block-table\"><table><thead><tr><th>Model<\/th><th>Load Size<\/th><th>Suitable for<\/th><\/tr><\/thead><tbody><tr><td><code>llama3.2:3b<\/code><\/td><td>2.0 GB<\/td><td>First launch, summarization, simple tasks<\/td><\/tr><tr><td><code>qwen3:4b<\/code><\/td><td>2.5 GB<\/td><td>Compact universal assistant<\/td><\/tr><tr><td><code>qwen3:8b<\/code><\/td><td>5.2 GB<\/td><td>Texts, analysis, multilingual tasks<\/td><\/tr><tr><td><code>deepseek-r1:8b<\/code><\/td><td>5.2 GB<\/td><td>Reasoning, mathematics and analytics<\/td><\/tr><tr><td><code>qwen3:30b<\/code><\/td><td>19 GB<\/td><td>More complex universal tasks<\/td><\/tr><tr><td><code>qwen3-coder:30b<\/code><\/td><td>19 GB<\/td><td>Programming and working with more context<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">The download sizes come from the official model cards for <a href=\"https:\/\/ollama.com\/library\/qwen3\" target=\"_blank\" rel=\"noopener\">Qwen 3<\/a>, <a href=\"https:\/\/ollama.com\/library\/qwen3-coder\" target=\"_blank\" rel=\"noopener\">Qwen3-Coder<\/a>, <a href=\"https:\/\/ollama.com\/library\/deepseek-r1\" target=\"_blank\" rel=\"noopener\">DeepSeek-R1<\/a>, and <a href=\"https:\/\/ollama.com\/library\/llama3.2\" target=\"_blank\" rel=\"noopener\">Llama 3.2<\/a>. They are file sizes, not exact RAM consumption figures.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Step 4: Check your local API<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">When Ollama is running, the API is available locally on port 11434. Checking the list of models:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>curl http:\/\/localhost:11434\/api\/tags<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">Example of a single request to a model:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>curl http:\/\/localhost:11434\/api\/generate \\\n  -d '{\"model\":\"qwen3:4b\",\"prompt\":\"Explain what a local LLM is\",\"stream\":false}'<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">Step 5: Install Open WebUI<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">If the terminal is inconvenient, Open WebUI adds an interface similar to the usual chat. First install Docker Desktop then run the command from <a href=\"https:\/\/docs.openwebui.com\/getting-started\/quick-start\/\" target=\"_blank\" rel=\"noopener\">official Open WebUI instructions<\/a>:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>docker run -d -p 3000:8080 \\\n  --add-host=host.docker.internal:host-gateway \\\n  -e OLLAMA_BASE_URL=http:\/\/host.docker.internal:11434 \\\n  -v open-webui:\/app\/backend\/data \\\n  --name open-webui --restart always \\\n  ghcr.io\/open-webui\/open-webui:main<\/code><\/pre>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/cifrum.kz\/wp-content\/uploads\/2026\/06\/ollama-open-webui-en.png\" alt=\"Local Open WebUI interface connected to Ollama\"\/><figcaption class=\"wp-element-caption\">After starting the container, open <code>http:\/\/localhost:3000<\/code> and create a local administrator account.<\/figcaption><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Tag <code>:main<\/code> updated over time. For a stable working installation, Open WebUI recommends pinning a specific version of the image. Also, do not open port 3000 to the Internet without authentication, HTTPS and basic server security.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What to do if Ollama doesn&#8217;t work<\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li><strong>Command not found:<\/strong> restart the terminal; on macOS, check for the link in <code>\/usr\/local\/bin<\/code>.<\/li><li><strong>The model is too slow:<\/strong> choose a smaller model, reduce the context, and close memory-hogging applications.<\/li><li><strong>Using CPU instead of GPU:<\/strong> update the driver and check the video card with the official support list.<\/li><li><strong>Not enough space:<\/strong> remove unnecessary models via <code>ollama rm<\/code> or transfer the model catalog.<\/li><li><strong>Open WebUI doesn&#8217;t see Ollama:<\/strong> check if it responds <code>http:\/\/localhost:11434\/api\/tags<\/code>, and whether it is set correctly <code>OLLAMA_BASE_URL<\/code>.<\/li><\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">FAQ<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">Is Ollama completely free?<\/h3>\n\n<p>The tool itself is free. Each model has its own license that must be verified before commercial use. Cloud functions may also have separate terms and conditions.<\/p>\n\n\n<h3 class=\"wp-block-heading\">Can I use Ollama without a video card?<\/h3>\n\n<p>Yes, local models can run on the CPU, but generation is usually noticeably slower. Start with model 1B\u20133B.<\/p>\n\n\n<h3 class=\"wp-block-heading\">Does Ollama work without the Internet?<\/h3>\n\n<p>After installing and loading the local model &#8211; yes. The Internet will be needed to download and update models, as well as for cloud functions.<\/p>\n\n\n<h3 class=\"wp-block-heading\">Which model is better for the first launch?<\/h3>\n\n<p>For 8GB RAM start with <code>llama3.2:3b<\/code>. For 16 GB try <code>qwen3:4b<\/code>and then <code>qwen3:8b<\/code>, if the system retains sufficient memory.<\/p>\n\n\n<h2 class=\"wp-block-heading\">Conclusion<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">For the first acquaintance, just install Ollama in the official way, check <code>ollama --version<\/code> and launch a compact model. Don&#8217;t start with 30B models just because they look more powerful: a small model that fits entirely in available memory often gives a better, faster local experience.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>The cover and step-by-step images are designed as impersonal display screens. They do not contain real accounts, keys, home directories or other personal data.<\/em><\/p>\n\n\n\n<style>\nbody.single-post .cf-code-copy-wrap{position:relative;margin:1.5em 0}\nbody.single-post .cf-code-copy-wrap pre.wp-block-code{margin:0;padding-top:3.25rem}\nbody.single-post .cf-code-copy-button{position:absolute;top:.75rem;right:.75rem;z-index:2;border:1px solid #cbd4e5;border-radius:5px;background:#fff;color:#17305f;padding:.45rem .75rem;font-size:.85rem;font-weight:600;line-height:1.2;cursor:pointer}\nbody.single-post .cf-code-copy-button:hover,body.single-post .cf-code-copy-button:focus{background:#eef3ff;border-color:#405ccb;outline:none}\n@media(max-width:600px){body.single-post .cf-code-copy-button{font-size:.78rem;padding:.4rem .6rem}}\n<\/style>\n<script>\ndocument.addEventListener('DOMContentLoaded',function(){\n  document.querySelectorAll('body.single-post pre.wp-block-code').forEach(function(pre){\n    if(pre.parentElement.classList.contains('cf-code-copy-wrap'))return;\n    var wrap=document.createElement('div');\n    wrap.className='cf-code-copy-wrap';\n    pre.parentNode.insertBefore(wrap,pre);\n    wrap.appendChild(pre);\n    var button=document.createElement('button');\n    button.type='button';\n    button.className='cf-code-copy-button';\n    button.textContent='Copy';\n    button.setAttribute('aria-label','Copy code');\n    button.addEventListener('click',function(){\n      var code=pre.querySelector('code');\n      navigator.clipboard.writeText((code||pre).innerText).then(function(){\n        button.textContent='Copied';\n        window.setTimeout(function(){button.textContent='Copy'},1600);\n      });\n    });\n    wrap.insertBefore(button,pre);\n  });\n});\n<\/script>\n","protected":false},"excerpt":{"rendered":"<p>Install Ollama on macOS, Windows, or Linux, choose a local model, test the API, configure Open WebUI, and solve common problems.<\/p>\n","protected":false},"author":1,"featured_media":6582,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"rank_math_focus_keyword":"install Ollama","rank_math_title":"How to Install Ollama in 2026: Step-by-Step Guide","rank_math_description":"Install Ollama on macOS, Windows, or Linux, choose a local model, test the API, configure Open WebUI, and fix common problems.","rank_math_canonical_url":"","rank_math_seo_score":"","rank_math_pillar_content":"","rank_math_facebook_title":"","rank_math_facebook_description":"","rank_math_facebook_image":"","rank_math_facebook_image_id":"","rank_math_twitter_title":"","rank_math_twitter_description":"","rank_math_twitter_image":"","rank_math_twitter_image_id":"","rank_math_news_sitemap_genre":"","rank_math_news_sitemap_keywords":"","rank_math_news_sitemap_stock_tickers":"","rank_math_robots":"","rank_math_advanced_robots":"","rank_math_schema_News":"","footnotes":""},"categories":[2104,1018],"tags":[],"class_list":["post-6588","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence-en","category-novosti"],"acf":[],"_links":{"self":[{"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/posts\/6588","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/comments?post=6588"}],"version-history":[{"count":1,"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/posts\/6588\/revisions"}],"predecessor-version":[{"id":6590,"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/posts\/6588\/revisions\/6590"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/media\/6582"}],"wp:attachment":[{"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/media?parent=6588"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/categories?post=6588"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cifrum.kz\/en\/wp-json\/wp\/v2\/tags?post=6588"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}