{"id":32750,"date":"2026-11-17T15:56:10","date_gmt":"2026-11-17T14:56:10","guid":{"rendered":"https:\/\/charlyhayoz.ch\/?p=32750"},"modified":"2026-11-17T15:56:13","modified_gmt":"2026-11-17T14:56:13","slug":"which-gpu-for-your-local-ai-calculate-it-in-10-seconds","status":"publish","type":"post","link":"https:\/\/charlyhayoz.ch\/en\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/","title":{"rendered":"Which GPU Should You Choose for Your On-Premises AI? The Calculation in 10 Seconds"},"content":{"rendered":"<p class=\"wp-block-paragraph\"><a href=\"https:\/\/www.linkedin.com\/in\/charlyhayoz\/\"><\/a>Tokens are like chips in a casino\u2014you burn through them really fast, and they're expensive! So you start thinking, why not host them locally? Plus, that way we'll have full control.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">But what resources are needed, how much VRAM (video memory\/GPU), and how do you calculate and budget for it?<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">It's very simple\u2014just go to this calculator: <a href=\"https:\/\/apxml.com\/tools\/vram-calculator\">https:\/\/apxml.com\/tools\/vram-calculator<\/a><\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/media.licdn.com\/dms\/image\/v2\/D4E12AQFBXKsnzqaj5A\/article-inline_image-shrink_1000_1488\/B4EaCkJN03IUAI-\/0\/1789460274803?e=1796256000&amp;v=beta&amp;t=YnCKxtweJXlloW2bhV2Q3J0XTDQWF31RuTltjm7vTag\" alt=\"Article content\"\/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Choose your category: <strong>inference \/ fine-tuning<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Sound <strong>model<\/strong>, specifically the latest DeepSeek V4.1 Flash<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The <strong>quantization<\/strong>, that is, model compression. We reduce the model's precision to save space. Generally, we choose INT4, which provides excellent compression (~70%) while maintaining acceptable quality.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Visit <strong>KV Cache Quantization<\/strong>, this is input cache compression. For each incoming request, it must be encoded and stored, which takes up space.<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/media.licdn.com\/dms\/image\/v2\/D4E12AQHGRU0SuQk1pQ\/article-inline_image-shrink_1000_1488\/B4EaCkKHJEJwAI-\/0\/1789460509570?e=1796256000&amp;v=beta&amp;t=_QCUsT5tvDZcwd60rPAoGiAxG61r7UYOt8tArK9SD30\" alt=\"Article content\"\/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Next, we configure the operational variables for our model\u2014that is, how we\u2019re going to use it.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>BatchSize:<\/strong> The number of requests processed at the same time. If there are 32, our model is capable of processing 32 requests at the same time.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Sequence Length:<\/strong> The token length of our input and output. The longer it is, the more time it takes us <strong>KV Cache<\/strong>. This depends on the expected queries. If you're processing large documents, you'll need a large sequence (&gt; 32,000); if you're processing comments, you'll need a smaller one (8,000, for example).<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">And <strong>Concurrent Users<\/strong> : The number of users we expect to be online at the same time.<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/media.licdn.com\/dms\/image\/v2\/D4E12AQGe7cJCT5lR6w\/article-inline_image-shrink_400_744\/B4EaCkKVIvJ4AQ-\/0\/1789460566794?e=1796256000&amp;v=beta&amp;t=5_-GOqAFL9TRS7Az1Gkpx00Dgsuc2e1OPFysXBTbqOs\" alt=\"Article content\"\/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">And then, <strong>Here you go<\/strong>, we have the necessary VRAM (GPU) to run our model locally, depending on our system configuration.<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/media.licdn.com\/dms\/image\/v2\/D4E12AQGNN6mLYvs_RA\/article-inline_image-shrink_1500_2232\/B4EaCkMRJpHMAQ-\/0\/1789461074804?e=1796256000&amp;v=beta&amp;t=MuvN5gGp-Q_viSMaXFZjOuUW7kU37JZBj8GHKG1sa7M\" alt=\"Article content\"\/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">As you can see here, the bill is steep. <strong>282.7 GB of VRAM.<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">At a minimum, I'll need 6x NVIDIA RTX 6000 Ada cards with 48 GB of memory (~60,000$) or a Mac Studio M3 Ultra with 512 GB of unified memory (~15,000$).<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Interestingly, you can also see the <strong>Generation Speed,<\/strong> The number of tokens generated per second, which is very important for the speed of our system.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">We can also compare the cost to that of the cloud. If I were to rent this same infrastructure in the cloud, it would cost me roughly $8.40 per hour. That is, <strong>200$ per day, 6000$ per month, 72000$ per year<\/strong>. It\u2019s clear, then, that investing in a Mac Studio M3 Ultra (~15,000$) can be <strong>Payback in less than 3 months<\/strong>.<\/p>","protected":false},"excerpt":{"rendered":"<p>Les tokens, c&rsquo;est comme les jetons dans un casino, on en crame tr\u00e8s vite et \u00e7a co\u00fbte cher ! Et l\u00e0 on se dit, mais pourquoi pas h\u00e9berger en local ? En plus, on sera souverain. Mais quelles ressources, combien de VRAM (m\u00e9moire vid\u00e9o \/ GPU), comment le calculer et le budg\u00e9tiser ? C&rsquo;est tr\u00e8s [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":32751,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55,60,65],"tags":[],"class_list":["post-32750","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-articles","category-development-logiciel","category-intelligence-artificielle"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v23.2 (Yoast SEO v23.2) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Quel GPU pour votre IA locale ? Le calcul en 10 secondes<\/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:\/\/charlyhayoz.ch\/en\/articles\/which-gpu-for-your-local-ai-calculate-it-in-10-seconds\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Quel GPU pour votre IA locale ? Le calcul en 10 secondes\" \/>\n<meta property=\"og:description\" content=\"Les tokens, c&rsquo;est comme les jetons dans un casino, on en crame tr\u00e8s vite et \u00e7a co\u00fbte cher ! Et l\u00e0 on se dit, mais pourquoi pas h\u00e9berger en local ? En plus, on sera souverain. Mais quelles ressources, combien de VRAM (m\u00e9moire vid\u00e9o \/ GPU), comment le calculer et le budg\u00e9tiser ? C&rsquo;est tr\u00e8s [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/charlyhayoz.ch\/en\/articles\/which-gpu-for-your-local-ai-calculate-it-in-10-seconds\/\" \/>\n<meta property=\"og:site_name\" content=\"Solutions IA sur mesure \u2013 Charly, expert en LLM &amp; Deep Learning\" \/>\n<meta property=\"article:published_time\" content=\"2026-11-17T14:56:10+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-11-17T14:56:13+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png\" \/>\n\t<meta property=\"og:image:width\" content=\"830\" \/>\n\t<meta property=\"og:image:height\" content=\"467\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"charly.hayoz\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"charly.hayoz\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/\"},\"author\":{\"name\":\"charly.hayoz\",\"@id\":\"https:\/\/charlyhayoz.ch\/#\/schema\/person\/3e574e6e75374de64cc525e08ac89233\"},\"headline\":\"Quel GPU pour votre IA locale ? Le calcul en 10 secondes\",\"datePublished\":\"2026-11-17T14:56:10+00:00\",\"dateModified\":\"2026-11-17T14:56:13+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/\"},\"wordCount\":445,\"publisher\":{\"@id\":\"https:\/\/charlyhayoz.ch\/#\/schema\/person\/3e574e6e75374de64cc525e08ac89233\"},\"image\":{\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png\",\"articleSection\":[\"Articles\",\"D\u00e9veloppement logiciel\",\"Intelligence artificielle\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/\",\"url\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/\",\"name\":\"Quel GPU pour votre IA locale ? Le calcul en 10 secondes\",\"isPartOf\":{\"@id\":\"https:\/\/charlyhayoz.ch\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png\",\"datePublished\":\"2026-11-17T14:56:10+00:00\",\"dateModified\":\"2026-11-17T14:56:13+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#primaryimage\",\"url\":\"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png\",\"contentUrl\":\"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png\",\"width\":830,\"height\":467,\"caption\":\"Un anneau de progression circulaire indique une utilisation de la VRAM de 100,0 % en rouge. En dessous, le texte affiche \u00ab INSUFFICIENT \u00bb, suivi d\u2019un besoin de 287,2 GB de VRAM pour une limite de 12 GB.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\/\/charlyhayoz.ch\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Quel GPU pour votre IA locale ? Le calcul en 10 secondes\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/charlyhayoz.ch\/#website\",\"url\":\"https:\/\/charlyhayoz.ch\/\",\"name\":\"Charly Hayoz\",\"description\":\"Ma seule limite, votre imagination\",\"publisher\":{\"@id\":\"https:\/\/charlyhayoz.ch\/#\/schema\/person\/3e574e6e75374de64cc525e08ac89233\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/charlyhayoz.ch\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\/\/charlyhayoz.ch\/#\/schema\/person\/3e574e6e75374de64cc525e08ac89233\",\"name\":\"charly.hayoz\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/charlyhayoz.ch\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2021\/09\/LogoComplet@1.5x.png\",\"contentUrl\":\"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2021\/09\/LogoComplet@1.5x.png\",\"width\":145,\"height\":43,\"caption\":\"charly.hayoz\"},\"logo\":{\"@id\":\"https:\/\/charlyhayoz.ch\/#\/schema\/person\/image\/\"},\"sameAs\":[\"https:\/\/charlyhayoz.ch\"]}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Which GPU Should You Choose for Your On-Premises AI? The Calculation in 10 Seconds","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:\/\/charlyhayoz.ch\/en\/articles\/which-gpu-for-your-local-ai-calculate-it-in-10-seconds\/","og_locale":"en_US","og_type":"article","og_title":"Quel GPU pour votre IA locale ? Le calcul en 10 secondes","og_description":"Les tokens, c&rsquo;est comme les jetons dans un casino, on en crame tr\u00e8s vite et \u00e7a co\u00fbte cher ! Et l\u00e0 on se dit, mais pourquoi pas h\u00e9berger en local ? En plus, on sera souverain. Mais quelles ressources, combien de VRAM (m\u00e9moire vid\u00e9o \/ GPU), comment le calculer et le budg\u00e9tiser ? C&rsquo;est tr\u00e8s [&hellip;]","og_url":"https:\/\/charlyhayoz.ch\/en\/articles\/which-gpu-for-your-local-ai-calculate-it-in-10-seconds\/","og_site_name":"Solutions IA sur mesure \u2013 Charly, expert en LLM &amp; Deep Learning","article_published_time":"2026-11-17T14:56:10+00:00","article_modified_time":"2026-11-17T14:56:13+00:00","og_image":[{"width":830,"height":467,"url":"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png","type":"image\/png"}],"author":"charly.hayoz","twitter_card":"summary_large_image","twitter_misc":{"Written by":"charly.hayoz","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#article","isPartOf":{"@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/"},"author":{"name":"charly.hayoz","@id":"https:\/\/charlyhayoz.ch\/#\/schema\/person\/3e574e6e75374de64cc525e08ac89233"},"headline":"Quel GPU pour votre IA locale ? Le calcul en 10 secondes","datePublished":"2026-11-17T14:56:10+00:00","dateModified":"2026-11-17T14:56:13+00:00","mainEntityOfPage":{"@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/"},"wordCount":445,"publisher":{"@id":"https:\/\/charlyhayoz.ch\/#\/schema\/person\/3e574e6e75374de64cc525e08ac89233"},"image":{"@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#primaryimage"},"thumbnailUrl":"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png","articleSection":["Articles","D\u00e9veloppement logiciel","Intelligence artificielle"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/","url":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/","name":"Which GPU Should You Choose for Your On-Premises AI? The Calculation in 10 Seconds","isPartOf":{"@id":"https:\/\/charlyhayoz.ch\/#website"},"primaryImageOfPage":{"@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#primaryimage"},"image":{"@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#primaryimage"},"thumbnailUrl":"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png","datePublished":"2026-11-17T14:56:10+00:00","dateModified":"2026-11-17T14:56:13+00:00","breadcrumb":{"@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#primaryimage","url":"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png","contentUrl":"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2026\/11\/1789461530590.png","width":830,"height":467,"caption":"Un anneau de progression circulaire indique une utilisation de la VRAM de 100,0 % en rouge. En dessous, le texte affiche \u00ab INSUFFICIENT \u00bb, suivi d\u2019un besoin de 287,2 GB de VRAM pour une limite de 12 GB."},{"@type":"BreadcrumbList","@id":"https:\/\/charlyhayoz.ch\/articles\/quel-gpu-pour-votre-ia-locale-le-calcul-en-10-secondes\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/charlyhayoz.ch\/"},{"@type":"ListItem","position":2,"name":"Quel GPU pour votre IA locale ? Le calcul en 10 secondes"}]},{"@type":"WebSite","@id":"https:\/\/charlyhayoz.ch\/#website","url":"https:\/\/charlyhayoz.ch\/","name":"Charly Hayoz","description":"My only limit is your imagination","publisher":{"@id":"https:\/\/charlyhayoz.ch\/#\/schema\/person\/3e574e6e75374de64cc525e08ac89233"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/charlyhayoz.ch\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"https:\/\/charlyhayoz.ch\/#\/schema\/person\/3e574e6e75374de64cc525e08ac89233","name":"charly.hayoz","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/charlyhayoz.ch\/#\/schema\/person\/image\/","url":"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2021\/09\/LogoComplet@1.5x.png","contentUrl":"https:\/\/charlyhayoz.ch\/wp-content\/uploads\/2021\/09\/LogoComplet@1.5x.png","width":145,"height":43,"caption":"charly.hayoz"},"logo":{"@id":"https:\/\/charlyhayoz.ch\/#\/schema\/person\/image\/"},"sameAs":["https:\/\/charlyhayoz.ch"]}]}},"_links":{"self":[{"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/posts\/32750","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/comments?post=32750"}],"version-history":[{"count":1,"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/posts\/32750\/revisions"}],"predecessor-version":[{"id":32755,"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/posts\/32750\/revisions\/32755"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/media\/32751"}],"wp:attachment":[{"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/media?parent=32750"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/categories?post=32750"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/charlyhayoz.ch\/en\/wp-json\/wp\/v2\/tags?post=32750"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}