{"id":2694,"date":"2026-09-13T20:13:01","date_gmt":"2026-09-13T20:13:01","guid":{"rendered":"https:\/\/convly.ai\/?p=2694"},"modified":"2026-09-13T20:13:01","modified_gmt":"2026-09-13T20:13:01","slug":"what-is-lm-studio","status":"publish","type":"post","link":"https:\/\/convly.ai\/es\/what-is-lm-studio\/","title":{"rendered":"Qu\u00e9 es LM Studio"},"content":{"rendered":"<div class=\"convly-tldr\">\n<ul>\n<li><strong>LM Studio is a free desktop application<\/strong> for discovering, downloading and running large language models locally on Windows, macOS and Linux.<\/li>\n<li>It bundles a <strong>chat UI, a model browser (Hugging Face search) and an OpenAI-compatible local HTTP server<\/strong> so existing SDKs point at <code>http:\/\/localhost:1234\/v1<\/code> with no code changes.<\/li>\n<li>It runs quantised GGUF models via <strong>llama.cpp<\/strong> on all platforms and <strong>MLX<\/strong> models on Apple Silicon; a command-line tool called <code>lms<\/code> ships alongside the GUI.<\/li>\n<li>Practical fit depends on VRAM: an 8B model at 4-bit needs roughly 5&nbsp;GB, a 70B model roughly 40&nbsp;GB. Use the <a href=\"https:\/\/convly.ai\/llm-vram-calculator\/\">VRAM calculator<\/a> before downloading.<\/li>\n<\/ul>\n<\/div>\n<p><strong>LM Studio is a free, closed-source desktop application that lets you download and run open-weight large language models entirely on your own machine.<\/strong> It ships for Windows, macOS and Linux, bundles inference engines (llama.cpp on all platforms, MLX on Apple Silicon), provides a ChatGPT-style GUI, and exposes an OpenAI-compatible REST server on <code>localhost:1234<\/code> so applications written against the OpenAI SDK can talk to a local model unchanged.<\/p>\n<p>The app is developed by the team behind <a href=\"https:\/\/lmstudio.ai\/\" rel=\"noopener\" target=\"_blank\">lmstudio.ai<\/a>. It is free for personal use and, per the vendor&#8217;s <a href=\"https:\/\/lmstudio.ai\/work\" rel=\"noopener\" target=\"_blank\">work-use page<\/a>, also free for use at work; commercial redistribution has its own terms.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_87_1 counter-flat ez-toc-counter ez-toc-container-direction\">\n<label for=\"ez-toc-cssicon-toggle-item-6aa72b340dbdb\" 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-6aa72b340dbdb\"  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\/es\/what-is-lm-studio\/#What_LM_Studio_actually_does\" >What LM Studio actually does<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/convly.ai\/es\/what-is-lm-studio\/#Supported_platforms\" >Supported platforms<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/convly.ai\/es\/what-is-lm-studio\/#What_you_can_run_in_LM_Studio\" >What you can run in LM Studio<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/convly.ai\/es\/what-is-lm-studio\/#The_OpenAI-compatible_server\" >The OpenAI-compatible server<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/convly.ai\/es\/what-is-lm-studio\/#LM_Studio_vs_Ollama\" >LM Studio vs Ollama<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/convly.ai\/es\/what-is-lm-studio\/#When_to_use_LM_Studio_instead_of_a_hosted_API\" >When to use LM Studio instead of a hosted API<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/convly.ai\/es\/what-is-lm-studio\/#Practical_setup_checklist\" >Practical setup checklist<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/convly.ai\/es\/what-is-lm-studio\/#Frequently_asked_questions\" >Frequently asked questions<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"What_LM_Studio_actually_does\"><\/span>What LM Studio actually does<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>LM Studio combines four things that would otherwise be separate tools:<\/p>\n<ul>\n<li><strong>Model discovery.<\/strong> A built-in search UI queries <a href=\"https:\/\/huggingface.co\/\" rel=\"noopener\" target=\"_blank\">Hugging Face<\/a> for GGUF and MLX files. You pick a quantisation (Q4_K_M, Q5_K_M, Q6_K, Q8_0, etc.) and it downloads directly into a local models folder.<\/li>\n<li><strong>Chat UI.<\/strong> A multi-turn chat window with per-conversation system prompts, temperature\/top-p sliders, structured output (JSON schema), and support for attaching PDFs or images (the latter only with vision-capable models).<\/li>\n<li><strong>Local inference server.<\/strong> An HTTP endpoint at <code>http:\/\/localhost:1234\/v1<\/code> that speaks the OpenAI Chat Completions, Completions and Embeddings API surface. See the vendor&#8217;s <a href=\"https:\/\/lmstudio.ai\/docs\/app\/api\/endpoints\/openai\" rel=\"noopener\" target=\"_blank\">OpenAI-compatibility docs<\/a>.<\/li>\n<li><strong>CLI (<code>lms<\/code>).<\/strong> A command-line tool for scripting model loads, unloads and server control. Installation and commands are documented at <a href=\"https:\/\/lmstudio.ai\/docs\/cli\" rel=\"noopener\" target=\"_blank\">lmstudio.ai\/docs\/cli<\/a>.<\/li>\n<\/ul>\n<p>Under the hood, inference runs on <a href=\"https:\/\/github.com\/ggerganov\/llama.cpp\" rel=\"noopener\" target=\"_blank\">llama.cpp<\/a> for GGUF models and on <a href=\"https:\/\/github.com\/ml-explore\/mlx\" rel=\"noopener\" target=\"_blank\">Apple MLX<\/a> for MLX-format models on Apple Silicon. LM Studio ships prebuilt engine binaries and lets you switch or update them from the app&#8217;s runtime settings.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Supported_platforms\"><\/span>Supported platforms<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<table>\n<thead>\n<tr>\n<th>Platform<\/th>\n<th>Requirements (per vendor)<\/th>\n<th>Acceleration<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Windows<\/td>\n<td>x64 or ARM64; AVX2-capable CPU on x64<\/td>\n<td>CPU, NVIDIA CUDA, Vulkan (AMD\/Intel GPUs)<\/td>\n<\/tr>\n<tr>\n<td>macOS<\/td>\n<td>Apple Silicon (M1 or newer), macOS 13.4+<\/td>\n<td>Metal (llama.cpp) and MLX<\/td>\n<\/tr>\n<tr>\n<td>Linux<\/td>\n<td>x64, glibc 2.35+, distributed as AppImage<\/td>\n<td>CPU, NVIDIA CUDA, Vulkan<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>The current published requirements live on the <a href=\"https:\/\/lmstudio.ai\/download\" rel=\"noopener\" target=\"_blank\">official download page<\/a>; check there before installing, since exact minimums shift between releases.<\/p>\n<h3>Windows<\/h3>\n<p>Installer is a standard <code>.exe<\/code>. Models default to <code>%USERPROFILE%.lmstudiomodels<\/code>. NVIDIA GPUs use CUDA when a supported runtime is selected; other GPUs fall back to Vulkan. AVX2 is required on x64 CPUs, so very old processors are excluded.<\/p>\n<h3>macOS<\/h3>\n<p>Distributed as a <code>.dmg<\/code>. On Apple Silicon, MLX-format models are available in addition to GGUF and generally use unified memory efficiently. Models default to <code>~\/.lmstudio\/models<\/code>. Intel Macs are not supported by current builds.<\/p>\n<h3>Linux<\/h3>\n<p>Shipped as an <code>.AppImage<\/code>. Mark it executable (<code>chmod +x LM-Studio-*.AppImage<\/code>) and run it directly. NVIDIA GPUs use CUDA; AMD and Intel GPUs use Vulkan. There is no official <code>.deb<\/code> or <code>.rpm<\/code> at the time of writing &mdash; check the download page for the current packaging.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"What_you_can_run_in_LM_Studio\"><\/span>What you can run in LM Studio<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>LM Studio can load any GGUF model that llama.cpp supports, plus MLX models on Apple Silicon. What actually fits on your hardware is the constraint. Approximate 4-bit VRAM footprints from the <a href=\"https:\/\/convly.ai\/models\/\">Convly models database<\/a>:<\/p>\n<table>\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Context<\/th>\n<th>~VRAM at 4-bit<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/gemma-3-4b\/\">Gemma 3 4B<\/a><\/td>\n<td>128K<\/td>\n<td>~3 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/mistral-7b\/\">Mistral 7B<\/a><\/td>\n<td>32K<\/td>\n<td>~4.5 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/llama-3-1-8b\/\">Llama 3.1 8B<\/a><\/td>\n<td>128K<\/td>\n<td>~5 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/qwen3-8b\/\">Qwen3 8B<\/a><\/td>\n<td>128K<\/td>\n<td>~5 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/phi-4\/\">Phi-4<\/a><\/td>\n<td>16K<\/td>\n<td>~9 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/gemma-3-12b\/\">Gemma 3 12B<\/a><\/td>\n<td>128K<\/td>\n<td>~8 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/qwen3-14b\/\">Qwen3 14B<\/a><\/td>\n<td>128K<\/td>\n<td>~9 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/gemma-3-27b\/\">Gemma 3 27B<\/a><\/td>\n<td>128K<\/td>\n<td>~16 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/qwen3-32b\/\">Qwen3 32B<\/a><\/td>\n<td>128K<\/td>\n<td>~20 GB<\/td>\n<\/tr>\n<tr>\n<td><a href=\"https:\/\/convly.ai\/model\/llama-3-3-70b\/\">Llama 3.3 70B<\/a><\/td>\n<td>128K<\/td>\n<td>~40 GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Anything above roughly 40&nbsp;GB requires multi-GPU or high-VRAM cards. Very large models such as <a href=\"https:\/\/convly.ai\/model\/deepseek-r1\/\">DeepSeek R1<\/a> (~400&nbsp;GB at 4-bit) are not practical to run on a single desktop GPU. See the full <a href=\"https:\/\/convly.ai\/vram-requirements-every-major-llm-2026\/\">VRAM requirements table<\/a> and the <a href=\"https:\/\/convly.ai\/best-gpus-for-local-llms-2026\/\">GPU guide for local LLMs<\/a> before buying hardware.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"The_OpenAI-compatible_server\"><\/span>The OpenAI-compatible server<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The most useful feature for developers is the local server. Start it from the <strong>Developer<\/strong> tab in the GUI or via the CLI. Once running, it accepts standard OpenAI-style requests:<\/p>\n<pre><code>curl http:\/\/localhost:1234\/v1\/chat\/completions \n  -H \"Content-Type: application\/json\" \n  -d '{\n    \"model\": \"loaded-model-identifier\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]\n  }'<\/code><\/pre>\n<p>The Python SDK works by pointing <code>base_url<\/code> at the local server:<\/p>\n<pre><code>from openai import OpenAI\nclient = OpenAI(base_url=\"http:\/\/localhost:1234\/v1\", api_key=\"lm-studio\")<\/code><\/pre>\n<p>The <code>api_key<\/code> value is ignored by default but the field must be present because the OpenAI SDK requires it. Supported endpoints and any deviations from OpenAI&#8217;s schema are listed in the <a href=\"https:\/\/lmstudio.ai\/docs\/app\/api\/endpoints\/openai\" rel=\"noopener\" target=\"_blank\">API reference<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"LM_Studio_vs_Ollama\"><\/span>LM Studio vs Ollama<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The two are the most common ways to run local LLMs on a workstation. Rough shape of the difference:<\/p>\n<table>\n<thead>\n<tr>\n<th><\/th>\n<th>LM Studio<\/th>\n<th>Ollama<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Primary interface<\/td>\n<td>Desktop GUI (chat, model browser)<\/td>\n<td>CLI and HTTP API<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>Closed-source app; free for personal and work use<\/td>\n<td>Open source (MIT)<\/td>\n<\/tr>\n<tr>\n<td>Model source<\/td>\n<td>Hugging Face (GGUF, MLX) via in-app search<\/td>\n<td>Ollama model registry (with import from GGUF)<\/td>\n<\/tr>\n<tr>\n<td>Server<\/td>\n<td>OpenAI-compatible at <code>:1234<\/code><\/td>\n<td>Native API at <code>:11434<\/code>, OpenAI-compatible layer<\/td>\n<\/tr>\n<tr>\n<td>Apple Silicon MLX<\/td>\n<td>Yes<\/td>\n<td>No (llama.cpp only)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>If you want a point-and-click UI and MLX support on a Mac, LM Studio is the easier starting point. If you want a scriptable open-source stack and headless server, see the <a href=\"https:\/\/convly.ai\/what-is-ollama-complete-guide-2026\/\">Ollama guide<\/a> and <a href=\"https:\/\/convly.ai\/how-to-install-ollama-2026\/\">installation walkthrough<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"When_to_use_LM_Studio_instead_of_a_hosted_API\"><\/span>When to use LM Studio instead of a hosted API<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Local inference is a real tradeoff. The upside is privacy (nothing leaves the machine), predictable cost after hardware amortisation, and offline availability. The downside is capital cost, slower tokens\/second than a hosted GPU cluster, and no access to frontier proprietary models.<\/p>\n<p>For a rough sense of the cost boundary: hosted models on the <a href=\"https:\/\/convly.ai\/llm-leaderboard\/\">Convly LLM leaderboard<\/a> range from about $0.02 per million input tokens for small open models on serverless providers up to $10 in \/ $50 out per million tokens for frontier proprietary models. If your workload sits at the small-model end and you can tolerate 8B&ndash;30B quality, self-hosting on a single consumer GPU frequently wins on total cost. Run your own numbers with the <a href=\"https:\/\/convly.ai\/self-hosting-vs-api-calculator\/\">self-hosting vs API calculator<\/a> and the <a href=\"https:\/\/convly.ai\/ai-api-cost-calculator\/\">API cost calculator<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Practical_setup_checklist\"><\/span>Practical setup checklist<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ol>\n<li>Check VRAM. Anything larger than your GPU&#8217;s memory will spill to system RAM and slow down dramatically. Use the <a href=\"https:\/\/convly.ai\/llm-vram-calculator\/\">VRAM calculator<\/a>.<\/li>\n<li>Download LM Studio from <a href=\"https:\/\/lmstudio.ai\/download\" rel=\"noopener\" target=\"_blank\">lmstudio.ai\/download<\/a>. Do not install from third-party mirrors.<\/li>\n<li>In the app&#8217;s <strong>Discover<\/strong> tab, pick a model that fits. Start with a Q4_K_M quantisation for the best size\/quality tradeoff.<\/li>\n<li>Load the model. Watch the VRAM indicator; if it can&#8217;t fully offload to GPU, choose a smaller quant or a smaller model.<\/li>\n<li>Enable the server from the <strong>Developer<\/strong> tab if you plan to hit it from code. Confirm with <code>curl http:\/\/localhost:1234\/v1\/models<\/code>.<\/li>\n<\/ol>\n<p>For a step-by-step walkthrough with screenshots, see the <a href=\"https:\/\/convly.ai\/lm-studio-complete-guide-2026\/\">LM Studio complete guide<\/a>. For model shortlists tuned to local hardware, see <a href=\"https:\/\/convly.ai\/best-local-llms-to-run-on-ollama-2026\/\">best local models<\/a> (the recommendations apply equally to LM Studio, since both engines use llama.cpp).<\/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>Is LM Studio free?<\/h3>\n<p>Yes. LM Studio is free to download and use for personal and, per the vendor&#8217;s <a href=\"https:\/\/lmstudio.ai\/work\" rel=\"noopener\" target=\"_blank\">work-use policy<\/a>, professional use. The app itself is closed-source, but the models you run in it are open-weight models licensed by their respective publishers (Meta, Google, Alibaba, Mistral, etc.).<\/p>\n<h3>Does LM Studio send data to the cloud?<\/h3>\n<p>Inference runs entirely on your machine &mdash; prompts and responses do not leave the device. The app does connect out to Hugging Face when you search or download models, and it checks for updates. There is no telemetry of chat contents according to the vendor&#8217;s <a href=\"https:\/\/lmstudio.ai\/privacy\" rel=\"noopener\" target=\"_blank\">privacy page<\/a>; review it directly for the current policy.<\/p>\n<h3>What model formats does LM Studio support?<\/h3>\n<p>GGUF on all platforms (via llama.cpp) and MLX on Apple Silicon. Raw Hugging Face safetensors and PyTorch checkpoints are not supported directly &mdash; convert them to GGUF first, or download a pre-quantised GGUF that the community has already published.<\/p>\n<h3>Can I use LM Studio as a drop-in replacement for the OpenAI API?<\/h3>\n<p>For chat completions, completions and embeddings, largely yes: point the OpenAI SDK&#8217;s <code>base_url<\/code> at <code>http:\/\/localhost:1234\/v1<\/code> and existing code works. Features that depend on OpenAI-specific server behaviour (assistants, file API, image generation, moderation) are not implemented. Check the current <a href=\"https:\/\/lmstudio.ai\/docs\/app\/api\/endpoints\/openai\" rel=\"noopener\" target=\"_blank\">endpoint list<\/a>.<\/p>\n<h3>How much RAM or VRAM do I need?<\/h3>\n<p>Rule of thumb at 4-bit quantisation: model size in billions of parameters times ~0.6 gives GB of VRAM needed for weights, plus a few GB for KV cache at long contexts. A 7&ndash;8B model runs comfortably on an 8&nbsp;GB GPU; a 70B model needs roughly 40&nbsp;GB (see the Convly models database figures above). For a full breakdown by model, see <a href=\"https:\/\/convly.ai\/vram-requirements-every-major-llm-2026\/\">VRAM requirements<\/a>.<\/p>\n<h3>Does LM Studio support tool calling and structured outputs?<\/h3>\n<p>Yes for structured outputs via JSON schema, and tool\/function calling is supported for models whose chat templates advertise it (recent Llama, Qwen, Mistral, and Gemma releases in particular). The quality of tool calling depends on the underlying model, not on LM Studio itself. Test with your target model before committing to it in production.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>LM Studio is a free desktop application for discovering, downloading and running large language models locally on Windows, macOS and [\u2026]<\/p>\n","protected":false},"author":1,"featured_media":2695,"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-2694","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tutorials"],"_links":{"self":[{"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/posts\/2694","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/comments?post=2694"}],"version-history":[{"count":1,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/posts\/2694\/revisions"}],"predecessor-version":[{"id":2696,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/posts\/2694\/revisions\/2696"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/media\/2695"}],"wp:attachment":[{"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/media?parent=2694"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/categories?post=2694"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/convly.ai\/es\/wp-json\/wp\/v2\/tags?post=2694"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}