{"id":1085,"date":"2026-06-11T10:12:15","date_gmt":"2026-06-11T10:12:15","guid":{"rendered":"https:\/\/convly.ai\/rtx-50-super-for-ai-2026\/"},"modified":"2026-06-15T18:18:30","modified_gmt":"2026-06-15T18:18:30","slug":"rtx-50-super-for-ai-2026","status":"publish","type":"post","link":"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/","title":{"rendered":"RTX 5080 Super &#038; 5070 Super for AI: What the Leaked VRAM Upgrades Mean for Local LLMs (2026)"},"content":{"rendered":"<p>For gamers, the rumored <strong>RTX 50 Super<\/strong> refresh is about a few extra frames. For anyone running AI locally, it&#8217;s about the one number that actually limits you: <strong>VRAM<\/strong>. Leaks point to a big jump \u2014 <strong>24GB on the RTX 5080 Super<\/strong> et <strong>18GB on the RTX 5070 Super<\/strong> \u2014 and if accurate, that reshapes what models you can run on a consumer card. Here&#8217;s the honest, AI-focused breakdown \u2014 with a clear flag on what&#8217;s confirmed and what isn&#8217;t.<\/p>\n<div class=\"convly-tldr\">\n<h3>Principaux enseignements<\/h3>\n<ul>\n<li><strong>Not official yet.<\/strong> NVIDIA hasn&#8217;t confirmed the RTX 50 Super refresh \u2014 these are leaks, rumored for later in 2026.<\/li>\n<li><strong>The leaked VRAM jumps:<\/strong> RTX 5080 Super \u2192 <strong>24GB<\/strong> (from 16GB); RTX 5070 Super \u2192 <strong>18GB<\/strong> (from 12GB).<\/li>\n<li><strong>Why it matters for AI:<\/strong> VRAM, not raw speed, decides how large a local LLM you can run. More VRAM = bigger models.<\/li>\n<li><strong>What 24GB unlocks:<\/strong> comfortable 4-bit inference of up to ~30B-class models \u2014 a real step up from today&#8217;s 16GB cards.<\/li>\n<li><strong>Should you wait?<\/strong> Maybe \u2014 but a 2026 memory crunch and uncertain timing mean &#8220;available and affordable&#8221; is not guaranteed.<\/li>\n<\/ul>\n<\/div>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_84 counter-flat ez-toc-counter ez-toc-container-direction\">\n<label for=\"ez-toc-cssicon-toggle-item-6a35460232dab\" 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-6a35460232dab\"  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\/fr\/rtx-50-super-for-ai-2026\/#Is_the_RTX_50_Super_refresh_even_real\" >Is the RTX 50 Super refresh even real?<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#The_leaked_specs\" >The leaked specs<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#Why_VRAM_is_the_number_that_matters_for_local_AI\" >Why VRAM is the number that matters for local AI<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#What_you_could_actually_run\" >What you could actually run<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#What_about_AMD_and_Intel\" >What about AMD and Intel?<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#A_note_on_power_and_your_PSU\" >A note on power and your PSU<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#Should_you_wait_for_it\" >Should you wait for it?<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#RTX_50_Super_vs_current_options_for_AI\" >RTX 50 Super vs current options (for AI)<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#FAQ\" >FAQ<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#Bottom_line\" >R\u00e9sultat<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/convly.ai\/fr\/rtx-50-super-for-ai-2026\/#Related_articles\" >Articles connexes<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"Is_the_RTX_50_Super_refresh_even_real\"><\/span>Is the RTX 50 Super refresh even real?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Be clear-eyed here: <strong>NVIDIA has not officially announced an RTX 50 Super series.<\/strong> Everything below comes from hardware leakers, and the timeline has slipped repeatedly. As of mid-2026, reporting suggests the refresh is &#8220;back on track&#8221; for later in the year, with leaked specs pointing to meaningful VRAM upgrades \u2014 but nothing is confirmed, and launch timing (and especially pricing) could change.<\/p>\n<p>So treat this as <strong>a rumor worth understanding, not a product to count on<\/strong>. With that caveat firmly in place, the leaked specs are genuinely interesting for AI users.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"The_leaked_specs\"><\/span>The leaked specs<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<table class=\"convly-vs\">\n<thead>\n<tr>\n<th>Card (rumored)<\/th>\n<th>VRAM<\/th>\n<th>Notable leaked specs<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>RTX 5080 Super<\/td>\n<td class=\"convly-vs-winner\">24GB GDDR7<\/td>\n<td>~10,752 CUDA cores, 32Gbps, ~450W, +9\u201316% vs 5080<\/td>\n<\/tr>\n<tr>\n<td>RTX 5070 Ti Super<\/td>\n<td class=\"convly-vs-winner\">~24GB GDDR7<\/td>\n<td>Up from 16GB (specs less certain)<\/td>\n<\/tr>\n<tr>\n<td>RTX 5070 Super<\/td>\n<td>18GB GDDR7<\/td>\n<td>6,400 CUDA cores, 192-bit, 28Gbps, 275W<\/td>\n<\/tr>\n<tr>\n<td>RTX 5060 (Super?)<\/td>\n<td>12GB<\/td>\n<td>Entry tier, rumored to compete with AMD&#8217;s RX 9070 GRE<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>The pattern is consistent: NVIDIA is reportedly pushing <strong>more memory at each tier<\/strong>, which is exactly what the AI crowd has been asking for. The raw compute bumps (single-digit to mid-teens percentages) are modest; the VRAM bumps are the story.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Why_VRAM_is_the_number_that_matters_for_local_AI\"><\/span>Why VRAM is the number that matters for local AI<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>For gaming, GPU performance is mostly about cores and clocks. For <strong>running large language models locally<\/strong>, the binding constraint is almost always <strong>VRAM<\/strong> \u2014 because the entire model (plus its context) has to fit in memory to run fast. Run out of VRAM and the model either won&#8217;t load or spills into system RAM, where it crawls.<\/p>\n<p>That&#8217;s why a card&#8217;s memory capacity often matters more than its speed for AI. A faster GPU with too little VRAM simply can&#8217;t run a model that a slower, higher-memory card handles with ease. (For the full picture, see our guide to <a href=\"\/fr\/vram-requirements-every-major-llm-2026\/\">Exigences en mati\u00e8re de VRAM pour tous les principaux programmes d'\u00e9ducation et de formation tout au long de la vie<\/a>.)<\/p>\n<h2><span class=\"ez-toc-section\" id=\"What_you_could_actually_run\"><\/span>What you could actually run<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Here&#8217;s the practical payoff of the leaked memory tiers, using common 4-bit quantization:<\/p>\n<ul>\n<li><strong>24GB (RTX 5080 Super):<\/strong> comfortably runs <strong>up to ~30B-parameter models<\/strong> at 4-bit, with room for solid context \u2014 a genuine step up from the 16GB ceiling that forces today&#8217;s RTX 5080 owners to stop around 14B\u201320B. It also makes image and video generation far less cramped.<\/li>\n<li><strong>18GB (RTX 5070 Super):<\/strong> handles <strong>~14B-class models<\/strong> comfortably and runs smaller models fast \u2014 a meaningful upgrade over 12GB cards that struggle past 8B.<\/li>\n<li><strong>12GB (RTX 5060):<\/strong> fine for <strong>7B\u20138B models<\/strong> and lighter workloads.<\/li>\n<\/ul>\n<p>To be clear about the ceiling: even 24GB won&#8217;t run a <strong>70B model<\/strong> unquantized \u2014 those still need a high-memory workstation card, multiple GPUs, or a dedicated local-AI box. NVIDIA is steering serious &gt;70B local work toward its 96GB Blackwell Pro cards and the <a href=\"\/fr\/nvidia-digits-personal-ai-computer-review\/\">DGX\/RTX Spark line<\/a>, not the consumer Super refresh. But for the models most people actually run, 18\u201324GB is the sweet spot. Pair one with the <a href=\"\/fr\/best-local-llms-to-run-on-ollama-2026\/\">best local LLMs to run on Ollama<\/a> and you have a capable home AI rig.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"What_about_AMD_and_Intel\"><\/span>What about AMD and Intel?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The Super refresh wouldn&#8217;t exist in a vacuum. AMD has already shipped the <strong>Radeon RX 9070 GRE<\/strong> in 2026, and its next-generation RDNA 5 (UDNA) architecture isn&#8217;t expected until <strong>late 2027 or 2028<\/strong> \u2014 so NVIDIA&#8217;s mid-cycle refresh would land against AMD&#8217;s <em>current<\/em> lineup, not a new one. Intel&#8217;s Arc continues to fight for the budget tier. For AI specifically, AMD remains a viable local-inference option, though NVIDIA&#8217;s CUDA ecosystem still dominates most local-LLM tooling (weigh our <a href=\"\/fr\/amd-rocm-vs-nvidia-cuda-2026\/\">ROCm vs CUDA<\/a> breakdown before going red-team).<\/p>\n<p>The bigger force shaping all of this is the <strong>2026 memory crunch<\/strong>: surging demand for the high-bandwidth memory that AI accelerators consume has tightened supply and lifted prices across the GPU market. That&#8217;s the same pressure reportedly complicating the Super refresh&#8217;s timing \u2014 and a reason not to assume these cards will arrive cheap or in volume.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"A_note_on_power_and_your_PSU\"><\/span>A note on power and your PSU<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>One practical wrinkle from the leaks: the RTX 5080 Super&#8217;s rumored <strong>450W<\/strong> board power (up from 360W on the 5080) is a meaningful jump. If you plan around one, budget for a strong power supply \u2014 roughly an 850W unit or better for a single-GPU AI workstation \u2014 plus adequate cooling. For always-on local inference, that higher draw also means higher running costs than a 16GB card. It&#8217;s a reminder that &#8220;more VRAM&#8221; isn&#8217;t free: you pay for it in watts as well as dollars.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Should_you_wait_for_it\"><\/span>Should you wait for it?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Honestly, it depends on your timeline and tolerance for uncertainty:<\/p>\n<ul>\n<li><strong>If you can wait and you run local AI:<\/strong> the VRAM upgrade is worth watching closely \u2014 24GB at (hopefully) mainstream pricing would be the best value local-AI card NVIDIA has offered in a while.<\/li>\n<li><strong>If you need a GPU now:<\/strong> don&#8217;t hold your breath. The refresh isn&#8217;t confirmed, timing keeps slipping, and 2026&#8217;s <strong>memory shortage and AI-accelerator demand<\/strong> are squeezing consumer GPU supply and prices. A bird in the hand \u2014 a current <a href=\"\/fr\/best-gpus-for-local-llms-2026\/\">16GB+ card for local LLMs<\/a> \u2014 may beat waiting indefinitely for a rumor.<\/li>\n<li><strong>If you need &gt;70B models:<\/strong> the Super refresh isn&#8217;t your answer regardless; look at high-VRAM workstation cards or a dedicated local-AI device.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"RTX_50_Super_vs_current_options_for_AI\"><\/span>RTX 50 Super vs current options (for AI)<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<table class=\"convly-vs\">\n<thead>\n<tr>\n<th>Option<\/th>\n<th>VRAM<\/th>\n<th>Meilleur pour<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>RTX 5080 Super (rumored)<\/td>\n<td class=\"convly-vs-winner\">24GB<\/td>\n<td>Up to ~30B local models, if it ships<\/td>\n<\/tr>\n<tr>\n<td>RTX 5090 (available)<\/td>\n<td class=\"convly-vs-winner\">32GB<\/td>\n<td>The current consumer VRAM king<\/td>\n<\/tr>\n<tr>\n<td>RTX 5080 (available)<\/td>\n<td>16GB<\/td>\n<td>Up to ~14\u201320B today<\/td>\n<\/tr>\n<tr>\n<td>RTX 5070 Super (rumored)<\/td>\n<td>18GB<\/td>\n<td>~14B local models, better value<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Note that the already-available <strong>RTX 5090 has 32GB<\/strong> \u2014 so if you need maximum consumer VRAM today and can afford it, it already exists. The Super refresh&#8217;s appeal is bringing more VRAM to the <em>mid<\/em> tiers at (hopefully) lower prices.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"FAQ\"><\/span>FAQ<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3>Is the RTX 5080 Super confirmed?<\/h3>\n<p>No. As of mid-2026, NVIDIA has not officially announced an RTX 50 Super series. The 24GB RTX 5080 Super and 18GB RTX 5070 Super come from hardware leaks, with a refresh rumored for later in 2026. Treat the specs and timing as unconfirmed.<\/p>\n<h3>How much VRAM does the RTX 5080 Super have?<\/h3>\n<p>According to leaks, 24GB of GDDR7 \u2014 up from 16GB on the standard RTX 5080. If accurate, that&#8217;s the single most important upgrade for AI users, since VRAM determines how large a local model you can run.<\/p>\n<h3>Is the RTX 5080 Super good for AI and local LLMs?<\/h3>\n<p>If the 24GB leak holds, yes \u2014 it would comfortably run up to roughly 30B-parameter models at 4-bit quantization, a clear step up from 16GB cards. It still won&#8217;t run unquantized 70B models, which need high-VRAM workstation hardware.<\/p>\n<h3>Why does VRAM matter more than speed for local AI?<\/h3>\n<p>Because the entire model and its context must fit in GPU memory to run fast. If a model doesn&#8217;t fit in VRAM, it either won&#8217;t load or spills into system RAM and slows to a crawl. So memory capacity usually sets the hard limit on what you can run; speed only affects how fast it runs once it fits.<\/p>\n<h3>Should I wait for the RTX 50 Super or buy now?<\/h3>\n<p>If you run local AI and can wait, it&#8217;s worth watching \u2014 24GB at a mainstream price would be excellent value. But it&#8217;s unconfirmed, the timeline keeps slipping, and a 2026 memory crunch is squeezing GPU supply and pricing. If you need a card now, a current 16GB+ GPU (or the 32GB RTX 5090) is the safer bet.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Bottom_line\"><\/span>R\u00e9sultat<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The rumored RTX 50 Super refresh is the rare GPU leak that matters more to AI users than to gamers \u2014 because the headline change is <strong>VRAM<\/strong>, the one spec that decides how large a local LLM you can run. If the <strong>24GB RTX 5080 Super<\/strong> et <strong>18GB RTX 5070 Super<\/strong> ship as leaked, they&#8217;d be the most genuinely useful local-AI consumer cards NVIDIA has offered in years.<\/p>\n<p>The catch is everything around the specs: it&#8217;s <strong>unconfirmed<\/strong>, the timing has slipped repeatedly, and 2026&#8217;s memory shortage makes pricing and availability a real question. Watch it closely if you run AI at home \u2014 but don&#8217;t put your build on hold for a card NVIDIA hasn&#8217;t even acknowledged yet.<\/p>\n<p><!--related-block--><\/p>\n<div class=\"convly-related\">\n<h2><span class=\"ez-toc-section\" id=\"Related_articles\"><\/span>Articles connexes<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/convly.ai\/fr\/best-mini-pc-for-local-ai-2026\/\">Best Mini PCs for Local AI in 2026: A Buyer&#039;s Guide<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/fr\/npu-vs-gpu-for-ai-2026\/\">NPU vs GPU for AI: What&#039;s the Difference? (2026)<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/fr\/nvidia-vera-rubin-explained-2026\/\">NVIDIA Vera Rubin Explained: The Next-Gen AI Platform That Cuts Inference Costs 10\u00d7 (2026)<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/fr\/rx-9070-xt-vs-rtx-5080-for-ai-2026\/\">AMD RX 9070 XT vs RTX 5080 for AI in 2026: Can AMD Punch Above Its Price?<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/fr\/rx-9070-xt-vs-rtx-5070-ti-for-ai-2026\/\">AMD RX 9070 XT vs RTX 5070 Ti for AI in 2026: Does ROCm Close the Gap?<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/fr\/rtx-pro-6000-vs-rtx-5090-for-ai-2026\/\">RTX Pro 6000 Blackwell vs RTX 5090 for AI in 2026: When Is 96GB Worth $5,500 More?<\/a><\/li>\n<\/ul>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>The rumored RTX 50 Super refresh could finally bump VRAM where it counts \u2014 24GB on the 5080 Super, 18GB on the 5070 Super. For running local LLMs, that&#8217;s the spec that matters. Here&#8217;s the honest picture.<\/p>","protected":false},"author":1,"featured_media":1087,"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":[248],"tags":[659,723,722,721,724],"class_list":["post-1085","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-gpus","tag-local-llm-gpu","tag-rtx-50-super","tag-rtx-5070-super","tag-rtx-5080-super","tag-vram-for-ai"],"_links":{"self":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/posts\/1085","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/comments?post=1085"}],"version-history":[{"count":5,"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/posts\/1085\/revisions"}],"predecessor-version":[{"id":1163,"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/posts\/1085\/revisions\/1163"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/media\/1087"}],"wp:attachment":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/media?parent=1085"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/categories?post=1085"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/tags?post=1085"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}