{"id":2775,"date":"2026-09-22T20:11:30","date_gmt":"2026-09-22T20:11:30","guid":{"rendered":"https:\/\/convly.ai\/?p=2775"},"modified":"2026-09-22T20:11:30","modified_gmt":"2026-09-22T20:11:30","slug":"ollama-remove-model","status":"publish","type":"post","link":"https:\/\/convly.ai\/pt\/ollama-remove-model\/","title":{"rendered":"Ollama Remove Model: Excluir LLMs locais em qualquer sistema operacional"},"content":{"rendered":"<div class=\"convly-tldr\">\n<ul>\n<li>To remove a model in Ollama, run <code>ollama rm &lt;model&gt;<\/code> (for example <code>ollama rm llama3.1:8b<\/code>). Use <code>ollama list<\/code> first to get the exact tag.<\/li>\n<li>The command deletes the manifest and dereferences the blobs; unreferenced blobs are pruned from the models directory, freeing disk immediately.<\/li>\n<li>Model storage lives under <code>~\/.ollama\/models<\/code> on macOS\/Linux and <code>%USERPROFILE%.ollamamodels<\/code> on Windows. Stop the Ollama service before manual cleanup.<\/li>\n<li>To remove every model at once, loop <code>ollama rm<\/code> over <code>ollama list<\/code>, or delete the <code>models\/<\/code> directory after stopping Ollama.<\/li>\n<\/ul>\n<\/div>\n<p>The short answer: <strong>use <code>ollama rm<\/code><\/strong>. Ollama exposes a single, cross-platform CLI for deleting local models, and it works identically on Windows, macOS and Linux. This guide covers the exact command, how to list what you have, where the files live, how to bulk-delete, and how to verify the space was actually reclaimed.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_88 counter-flat ez-toc-counter ez-toc-container-direction\">\n<label for=\"ez-toc-cssicon-toggle-item-6ab314d93ca42\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #000000;color:#000000\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #000000;color:#000000\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6ab314d93ca42\"  aria-label=\"Toggle\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/convly.ai\/pt\/ollama-remove-model\/#The_Command_ollama_rm\" >The Command: ollama rm<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/convly.ai\/pt\/ollama-remove-model\/#Where_Ollama_Stores_Models\" >Where Ollama Stores Models<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/convly.ai\/pt\/ollama-remove-model\/#Platform-Specific_Notes\" >Platform-Specific Notes<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/convly.ai\/pt\/ollama-remove-model\/#Verifying_the_Space_Was_Freed\" >Verifying the Space Was Freed<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/convly.ai\/pt\/ollama-remove-model\/#Removing_a_Model_via_the_REST_API\" >Removing a Model via the REST API<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/convly.ai\/pt\/ollama-remove-model\/#Common_Mistakes\" >Common Mistakes<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/convly.ai\/pt\/ollama-remove-model\/#Frequently_Asked_Questions\" >Frequently Asked Questions<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/convly.ai\/pt\/ollama-remove-model\/#Reference\" >Reference<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"The_Command_ollama_rm\"><\/span>The Command: <code>ollama rm<\/code><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>List installed models first so you use the right tag:<\/p>\n<pre><code>ollama list<\/code><\/pre>\n<p>Output looks like this:<\/p>\n<pre><code>NAME                    ID              SIZE      MODIFIED\nllama3.1:8b             42182419e950    4.7 GB    2 days ago\nqwen3:8b                a1b2c3d4e5f6    5.2 GB    1 week ago\ngemma3:4b               f6e5d4c3b2a1    3.3 GB    3 weeks ago<\/code><\/pre>\n<p>Then remove by name and tag:<\/p>\n<pre><code>ollama rm llama3.1:8b<\/code><\/pre>\n<p>You should see <code>deleted 'llama3.1:8b'<\/code>. If you omit the tag, Ollama defaults to <code>:latest<\/code>, which may not match what you actually have installed \u2014 always copy the tag from <code>ollama list<\/code>. The <code>rm<\/code> command is documented in the official CLI reference on the <a href=\"https:\/\/github.com\/ollama\/ollama\" rel=\"noopener\" target=\"_blank\">Ollama GitHub repository<\/a>.<\/p>\n<h3>Removing Multiple Models<\/h3>\n<p><code>ollama rm<\/code> accepts multiple arguments:<\/p>\n<pre><code>ollama rm llama3.1:8b qwen3:8b gemma3:4b<\/code><\/pre>\n<p>This is the safest bulk approach because Ollama handles blob dereferencing for you.<\/p>\n<h3>Removing All Models at Once<\/h3>\n<p>On macOS or Linux (bash\/zsh):<\/p>\n<pre><code>ollama list | tail -n +2 | awk '{print $1}' | xargs -r -n1 ollama rm<\/code><\/pre>\n<p>On Windows PowerShell:<\/p>\n<pre><code>ollama list | Select-Object -Skip 1 | ForEach-Object { ($_ -split 's+')[0] } | ForEach-Object { ollama rm $_ }<\/code><\/pre>\n<p>If the loop is fussy on your shell version, fall back to deleting them one at a time \u2014 the CLI syntax is stable, the piping isn&#8217;t.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Where_Ollama_Stores_Models\"><\/span>Where Ollama Stores Models<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Knowing the storage layout matters when you want to confirm disk was freed, migrate models to another drive, or clean up after a broken install.<\/p>\n<table>\n<thead>\n<tr>\n<th>OS<\/th>\n<th>Default models directory<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>macOS<\/td>\n<td><code>~\/.ollama\/models<\/code><\/td>\n<\/tr>\n<tr>\n<td>Linux<\/td>\n<td><code>~\/.ollama\/models<\/code> (user install) or <code>\/usr\/share\/ollama\/.ollama\/models<\/code> (systemd service install)<\/td>\n<\/tr>\n<tr>\n<td>Windows<\/td>\n<td><code>%USERPROFILE%.ollamamodels<\/code> (typically <code>C:Users&lt;you&gt;.ollamamodels<\/code>)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Inside that directory you&#8217;ll see two subfolders: <code>blobs\/<\/code> holds the raw weight and config chunks (content-addressed by SHA256), and <code>manifests\/<\/code> holds the small JSON files that map a name like <code>llama3.1:8b<\/code> to a set of blobs. When you run <code>ollama rm<\/code>, the manifest is deleted first, then any blob no longer referenced by another manifest is pruned. This is why removing one model that shares layers with another may free less space than you expect.<\/p>\n<p>Ollama&#8217;s storage paths are described in the project&#8217;s <a href=\"https:\/\/github.com\/ollama\/ollama\/tree\/main\/docs\" rel=\"noopener\" target=\"_blank\">documentation directory on GitHub<\/a>, including the <code>OLLAMA_MODELS<\/code> environment variable you can set to relocate the directory.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Platform-Specific_Notes\"><\/span>Platform-Specific Notes<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3>Windows<\/h3>\n<p>The CLI is identical: open PowerShell or Command Prompt and run <code>ollama rm &lt;model&gt;<\/code>. If a model appears to be locked, exit the Ollama tray icon (right-click \u2192 Quit Ollama) first \u2014 the background service may still hold a handle if you tried a manual folder delete. For a full wipe: quit Ollama from the tray, then delete <code>%USERPROFILE%.ollamamodels<\/code>. Reinstall instructions live in our <a href=\"https:\/\/convly.ai\/how-to-install-ollama-2026\/\">Ollama install guide<\/a>.<\/p>\n<h3>macOS<\/h3>\n<p>Run <code>ollama rm &lt;model&gt;<\/code> in Terminal. If you installed the Ollama.app, quit it from the menu bar before manually touching <code>~\/.ollama\/models<\/code>. To uninstall Ollama entirely, drag the app to Trash and delete <code>~\/.ollama<\/code>.<\/p>\n<h3>Linux<\/h3>\n<p>For a user install, <code>ollama rm<\/code> works as expected. For the systemd service install (the default from the curl installer), the models live under the <code>ollama<\/code> service user, typically <code>\/usr\/share\/ollama\/.ollama\/models<\/code>. Run the CLI as the same user that runs the service, or use <code>sudo -u ollama ollama rm &lt;model&gt;<\/code>. Stop the service before manual filesystem cleanup:<\/p>\n<pre><code>sudo systemctl stop ollama\nsudo rm -rf \/usr\/share\/ollama\/.ollama\/models\nsudo systemctl start ollama<\/code><\/pre>\n<h2><span class=\"ez-toc-section\" id=\"Verifying_the_Space_Was_Freed\"><\/span>Verifying the Space Was Freed<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>After removing a model, confirm two things:<\/p>\n<ol>\n<li><code>ollama list<\/code> no longer shows it.<\/li>\n<li>The models directory shrank. On macOS\/Linux: <code>du -sh ~\/.ollama\/models<\/code>. On Windows PowerShell: <code>(Get-ChildItem $env:USERPROFILE.ollamamodels -Recurse | Measure-Object -Property Length -Sum).Sum \/ 1GB<\/code>.<\/li>\n<\/ol>\n<p>Rough sanity checks for well-known models (weights only, from the <a href=\"https:\/\/convly.ai\/models\/\">Convly models database<\/a>, 4-bit quant on disk is close to VRAM footprint):<\/p>\n<table>\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Approx. on-disk size (4-bit)<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Gemma 3 4B<\/td>\n<td>~3 GB<\/td>\n<\/tr>\n<tr>\n<td>Mistral 7B<\/td>\n<td>~4.5 GB<\/td>\n<\/tr>\n<tr>\n<td>Llama 3.1 8B<\/td>\n<td>~5 GB<\/td>\n<\/tr>\n<tr>\n<td>Qwen3 8B<\/td>\n<td>~5 GB<\/td>\n<\/tr>\n<tr>\n<td>Phi-4<\/td>\n<td>~9 GB<\/td>\n<\/tr>\n<tr>\n<td>Gemma 3 27B<\/td>\n<td>~16 GB<\/td>\n<\/tr>\n<tr>\n<td>Qwen3 32B<\/td>\n<td>~20 GB<\/td>\n<\/tr>\n<tr>\n<td>Llama 3.3 70B<\/td>\n<td>~40 GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>If the freed space looks small, check whether another tag is still installed \u2014 for example, if you removed <code>llama3.1:8b<\/code> but <code>llama3.1:8b-instruct-q4_K_M<\/code> is still there, they may share blobs. To plan storage before installing a replacement, use the <a href=\"https:\/\/convly.ai\/llm-vram-calculator\/\">Convly VRAM calculator<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Removing_a_Model_via_the_REST_API\"><\/span>Removing a Model via the REST API<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Ollama also exposes a delete endpoint on its local HTTP server (default <code>http:\/\/localhost:11434<\/code>):<\/p>\n<pre><code>curl -X DELETE http:\/\/localhost:11434\/api\/delete -d '{\"name\": \"llama3.1:8b\"}'<\/code><\/pre>\n<p>The endpoint returns HTTP 200 on success and 404 if the model isn&#8217;t installed. This is useful for scripting cleanup on remote hosts or CI runners. The API surface is documented in the <a href=\"https:\/\/github.com\/ollama\/ollama\/tree\/main\/docs\" rel=\"noopener\" target=\"_blank\">Ollama docs<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Common_Mistakes\"><\/span>Common Mistakes<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><strong>Deleting files manually while Ollama is running.<\/strong> On Windows especially, this can leave dangling manifests. Always prefer <code>ollama rm<\/code>, and stop the service before touching the folder.<\/li>\n<li><strong>Confusing the tag.<\/strong> <code>ollama rm llama3.1<\/code> targets <code>llama3.1:latest<\/code>. If you pulled <code>llama3.1:8b<\/code>, that&#8217;s a different manifest and won&#8217;t be removed.<\/li>\n<li><strong>Expecting VRAM to change.<\/strong> Removing a model frees disk, not GPU memory. VRAM is only occupied while a model is loaded; use <code>ollama ps<\/code> to see what&#8217;s currently loaded and <code>ollama stop &lt;model&gt;<\/code> to unload it.<\/li>\n<li><strong>Forgetting custom Modelfile builds.<\/strong> Models you created with <code>ollama create mymodel -f Modelfile<\/code> show up in <code>ollama list<\/code> like any other and are removed with <code>ollama rm mymodel<\/code>.<\/li>\n<\/ul>\n<p>If you&#8217;re rethinking which models to keep, the <a href=\"https:\/\/convly.ai\/best-local-llms-to-run-on-ollama-2026\/\">best local models for Ollama<\/a> and the <a href=\"https:\/\/convly.ai\/llm-leaderboard\/\">LLM leaderboard<\/a> are useful for choosing replacements by size and capability. If disk pressure is pushing you toward API inference instead, run the numbers with the <a href=\"https:\/\/convly.ai\/self-hosting-vs-api-calculator\/\">self-hosting vs API calculator<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Frequently_Asked_Questions\"><\/span>Frequently Asked Questions<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3>Does <code>ollama rm<\/code> free disk space immediately?<\/h3>\n<p>Yes. When the last manifest referencing a blob is deleted, Ollama prunes the blob from <code>models\/blobs\/<\/code> on the spot. You can verify with <code>du -sh ~\/.ollama\/models<\/code> before and after. If two installed models share layers, only the layers unique to the removed model are freed.<\/p>\n<h3>How do I remove all Ollama models at once?<\/h3>\n<p>The cleanest way is to stop Ollama and delete the <code>models\/<\/code> directory under <code>~\/.ollama<\/code> (or <code>%USERPROFILE%.ollama<\/code> on Windows). Restart Ollama afterwards and <code>ollama list<\/code> will be empty. Alternatively, pipe <code>ollama list<\/code> into <code>xargs ollama rm<\/code> to remove them one by one through the CLI.<\/p>\n<h3>Can I remove a model that&#8217;s currently loaded in memory?<\/h3>\n<p>Not while it&#8217;s actively serving a request. Run <code>ollama ps<\/code> to see loaded models, <code>ollama stop &lt;model&gt;<\/code> to unload it, then <code>ollama rm &lt;model&gt;<\/code>. If a client keeps re-loading it, stop that client first.<\/p>\n<h3>Where does Ollama store models on Windows?<\/h3>\n<p>Under <code>%USERPROFILE%.ollamamodels<\/code>, which is normally <code>C:Users&lt;your-username&gt;.ollamamodels<\/code>. You can relocate this by setting the <code>OLLAMA_MODELS<\/code> environment variable to a different path \u2014 useful when your system drive is small and you want models on a secondary SSD. Restart Ollama for the change to take effect.<\/p>\n<h3>Does removing a model in Ollama also remove it from LM Studio or other tools?<\/h3>\n<p>No. Ollama, <a href=\"https:\/\/convly.ai\/lm-studio-complete-guide-2026\/\">LM Studio<\/a>, and llama.cpp each maintain their own model directories. Removing <code>llama3.1:8b<\/code> from Ollama has no effect on a GGUF file you downloaded separately for LM Studio.<\/p>\n<h3>Is there a way to remove only old or unused models?<\/h3>\n<p>Ollama doesn&#8217;t ship a built-in &#8220;prune unused&#8221; command. The <code>MODIFIED<\/code> column in <code>ollama list<\/code> shows the last time a model was pulled or refreshed, not last used, so it&#8217;s an imperfect proxy. For a stricter policy, script around <code>ollama list<\/code> and remove anything above a size threshold or older than a given date.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Reference\"><\/span>Reference<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/github.com\/ollama\/ollama\" rel=\"noopener\" target=\"_blank\">Ollama GitHub repository<\/a> \u2014 CLI reference including <code>ollama rm<\/code>.<\/li>\n<li><a href=\"https:\/\/github.com\/ollama\/ollama\/tree\/main\/docs\" rel=\"noopener\" target=\"_blank\">Ollama documentation directory<\/a> \u2014 API endpoints, environment variables, storage paths.<\/li>\n<li><a href=\"https:\/\/convly.ai\/what-is-ollama-complete-guide-2026\/\">Convly Ollama complete guide<\/a> \u2014 full workflow from install to inference.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>To remove a model in Ollama, run ollama rm &lt;model&gt; (for example ollama rm llama3.1:8b). Use ollama list first to [\u2026]<\/p>\n","protected":false},"author":1,"featured_media":2776,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"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":""}},"footnotes":""},"categories":[9],"tags":[],"class_list":["post-2775","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tutorials"],"_links":{"self":[{"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/posts\/2775","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/comments?post=2775"}],"version-history":[{"count":1,"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/posts\/2775\/revisions"}],"predecessor-version":[{"id":2777,"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/posts\/2775\/revisions\/2777"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/media\/2776"}],"wp:attachment":[{"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/media?parent=2775"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/categories?post=2775"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/convly.ai\/pt\/wp-json\/wp\/v2\/tags?post=2775"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}