{"id":285700,"date":"2025-11-16T00:06:14","date_gmt":"2025-11-16T00:06:14","guid":{"rendered":"https:\/\/www.newsbeep.com\/ca\/285700\/"},"modified":"2025-11-16T00:06:14","modified_gmt":"2025-11-16T00:06:14","slug":"running-your-own-local-open-source-ai-model-is-easy-heres-how","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ca\/285700\/","title":{"rendered":"Running Your Own Local Open-Source AI Model Is Easy\u2014Here&#8217;s How"},"content":{"rendered":"<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">If you\u2019re not a developer, then why in the world would you want to run an open-source AI model on your home computer?<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">It turns out there are a number of good reasons. And with free, open-source models getting better than ever\u2014and simple to use, with minimal hardware requirements\u2014now is a great time to give it a shot.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Here are a few reasons why open-source models are better than paying $20 a month to ChatGPT, Perplexity, or Google:<\/p>\n<p>It\u2019s free. No subscription fees.<br \/>\nYour data stays on your machine.<br \/>\nIt works offline, no internet required.<br \/>\nYou can train and customize your model for specific use cases, such as creative writing or&#8230; well, anything.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">The barrier to entry has collapsed. Now there are specialized programs that let users experiment with AI without all the hassle of installing libraries, dependencies, and plugins independently. Just about anyone with a fairly recent computer can do it: A mid-range laptop or desktop with 8GB of video memory can run surprisingly capable models, and some models run on 6GB or even 4GB of VRAM. And for Apple, any M-series chip (from the last few years) will be able to run optimized models.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">The software is free, the setup takes minutes, and the most intimidating step\u2014choosing which tool to use\u2014comes down to a simple question: Do you prefer clicking buttons or typing commands?<\/p>\n<p>LM Studio vs. Ollama<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Two platforms dominate the local AI space, and they approach the problem from opposite angles.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\"><a href=\"https:\/\/lmstudio.ai\/\" target=\"_blank\" rel=\"nofollow external noopener\" class=\"sc-adb616fe-0 bJsyml\">LM Studio<\/a> wraps everything in a polished graphical interface. You can simply download the app, browse a built-in model library, click to install, and start chatting. The experience mirrors using ChatGPT, except the processing happens on your hardware. Windows, Mac, and Linux users get the same smooth experience. For newcomers, this is the obvious starting point.<\/p>\n<p><img alt=\"\" loading=\"lazy\" width=\"1489\" height=\"938\" decoding=\"async\" data-nimg=\"1\" class=\"object-contain object-center w-full\" style=\"color:transparent\"   src=\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2025\/11\/image7.png@webp.webp\"\/><\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\"><a href=\"https:\/\/ollama.com\/\" target=\"_blank\" rel=\"nofollow external noopener\" class=\"sc-adb616fe-0 bJsyml\">Ollama<\/a> is aimed at developers and power users who live in the terminal. Install via command line, pull models with a single command, and then script or automate to your heart&#8217;s content. It&#8217;s lightweight, fast, and integrates cleanly into programming workflows.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">The learning curve is steeper, but the payoff is flexibility. It is also what power users choose for versatility and customizability.<\/p>\n<p><img alt=\"\" loading=\"lazy\" width=\"1449\" height=\"1174\" decoding=\"async\" data-nimg=\"1\" class=\"object-contain object-center w-full\" style=\"color:transparent\"   src=\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2025\/11\/image3.png@webp.webp\"\/><\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Both tools run the same underlying models using identical optimization engines. Performance differences are negligible.<\/p>\n<p>Setting up LM Studio<img alt=\"\" loading=\"lazy\" width=\"993\" height=\"794\" decoding=\"async\" data-nimg=\"1\" class=\"object-contain object-center w-full\" style=\"color:transparent\"   src=\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2025\/11\/image6.png@webp.webp\"\/><\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Visit <a href=\"https:\/\/lmstudio.ai\/\" target=\"_blank\" rel=\"nofollow external noopener\" class=\"sc-adb616fe-0 bJsyml\">https:\/\/lmstudio.ai\/<\/a> and download the installer for your operating system. The file weighs about 540MB. Run the installer and follow the prompts. Launch the application.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Hint 1: If it asks you which type of user you are, pick \u201cdeveloper.\u201d The other profiles simply hide options to make things easier.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Hint 2: It will recommend downloading OSS, OpenAI\u2019s open-source AI model. Instead, click \u201cskip\u201d for now; there are better, smaller models that will do a better job.<\/p>\n<p>VRAM: The key to running local AI<img alt=\"\" loading=\"lazy\" width=\"1494\" height=\"942\" decoding=\"async\" data-nimg=\"1\" class=\"object-contain object-center w-full\" style=\"color:transparent\"   src=\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2025\/11\/image4.png@webp.webp\"\/><\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Once you have installed LM Studio, the program will be ready to run and will look like this:<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Now you need to download a model before your LLM will work. And the more powerful the model, the more resources it will require.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">The critical resource is VRAM, or video memory on your graphics card. LLMs load into VRAM during inference. If you don&#8217;t have enough space, then performance collapses and the system must resort to slower system RAM. You&#8217;ll want to avoid that by having enough VRAM for the model you want to run.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">To know how much VRAM you have, you can enter the Windows task manager (control+alt+del) and click on the GPU tab, making sure you have selected the dedicated graphics card and not the integrated graphics on your Intel\/AMD processor.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">You will see how much VRAM you have in the &#8220;Dedicated GPU memory&#8221; section.<\/p>\n<p><img alt=\"\" loading=\"lazy\" width=\"1502\" height=\"946\" decoding=\"async\" data-nimg=\"1\" class=\"object-contain object-center w-full\" style=\"color:transparent\"   src=\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2025\/11\/image5.png@webp.webp\"\/><\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">On M-Series Macs, things are easier since they share RAM and VRAM. The amount of RAM on your machine will equal the VRAM you can access.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">To check, click on the Apple logo, then click on &#8220;About.&#8221; See Memory? That&#8217;s how much VRAM you have.<\/p>\n<p><img alt=\"\" loading=\"lazy\" width=\"693\" height=\"1010\" decoding=\"async\" data-nimg=\"1\" class=\"object-contain object-center w-full\" style=\"color:transparent\"   src=\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2025\/11\/image8.png@webp.webp\"\/><\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">You\u2019ll want at least 8GB of VRAM. Models in the 7-9 billion parameter range, compressed using 4-bit quantization, fit comfortably while delivering strong performance. You\u2019ll know if a model is quantized because developers usually disclose it in the name. If you see BF, FP or GGUF in the name, then you are looking at a quantized model. The lower the number (FP32, FP16, FP8, FP4), the fewer resources it will consume.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">It\u2019s not apples to apples, but imagine quantization as the resolution of your screen. You will see the same image in 8K, 4K, 1080p, or 720p. You will be able to grasp everything no matter the resolution, but zooming in and being picky at the details will reveal that a 4K image has more information that a 720p, but will require more memory and resources to render.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">But ideally, if you are really serious, then you should buy a nice gaming GPU with 24GB of VRAM. It doesn\u2019t matter if it is new or not, and it doesn\u2019t matter how fast or powerful it is. In the land of AI, VRAM is king.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Once you know how much VRAM you can tap, then you can figure out which models you can run by going to the <a href=\"https:\/\/huggingface.co\/spaces\/DavidAU\/GGUF-Model-VRAM-Calculator\" target=\"_blank\" rel=\"nofollow external noopener\" class=\"sc-adb616fe-0 bJsyml\">VRAM Calculator<\/a>.\u00a0 Or, simply start with smaller models of less than 4 billion parameters and then step up to bigger ones until your computer tells you that you don\u2019t have enough memory. (More on this technique in a bit.)<\/p>\n<p>Downloading your models<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Once you know your hardware\u2019s limits, then it&#8217;s time to download a model. Click on the magnifying glass icon on the left sidebar and search for the model by name.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Qwen and DeepSeek are good models to use to begin your journey. Yes, they are Chinese, but if you are worried about being spied on, then you can rest easy. When you run your LLM locally, nothing leaves your machine, so you won\u2019t be spied on by either the Chinese, the U.S. government, or any corporate entities.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">As for viruses, everything we&#8217;re recommending comes via Hugging Face, where software is instantly checked for spyware and other malware. But for what it&#8217;s worth, the best American model is Meta&#8217;s Llama, so you may want to pick that if you are a patriot. (We offer other recommendations in the final section.)<\/p>\n<p>\ufeff<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Note that models do behave differently depending on the training dataset and the fine-tuning techniques used to build them. Elon Musk&#8217;s Grok notwithstanding, there is no such a thing as an unbiased model because there is no such thing as unbiased information. So pick your poison depending on how much you care about geopolitics.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">For now, download both the 3B (smaller less capable model) and 7B versions. If you can run the 7B, then delete the 3B (and try downloading and running the 13B version and so on). If you cannot run the 7B version, then delete it and use the 3B version.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Once downloaded, load the model from the My Models section. The chat interface appears. Type a message. The model responds. Congratulations: You&#8217;re running a local AI.<\/p>\n<p><img alt=\"\" loading=\"lazy\" width=\"1489\" height=\"938\" decoding=\"async\" data-nimg=\"1\" class=\"object-contain object-center w-full\" style=\"color:transparent\"   src=\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2025\/11\/image7.png@webp.webp\"\/>Giving your model internet access<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Out of the box, local models can&#8217;t browse the web. They&#8217;re isolated by design, so you will iterate with them based on their internal knowledge. They will work fine for writing short stories, answering questions, doing some coding, etc. But they won\u2019t give you the latest news, tell you the weather, check your email, or schedule meetings for you.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\"><a href=\"https:\/\/decrypt.co\/346185\/complete-idiots-guide-mcp-giving-your-ai-web-superpowers\" target=\"_blank\" class=\"sc-adb616fe-0 bJsyml\" rel=\"nofollow noopener\">Model Context Protocol servers<\/a> change this.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">MCP servers act as bridges between your model and external services. Want your AI to search Google, check GitHub repositories, or read websites? MCP servers make it possible. LM Studio added MCP support in version 0.3.17, accessible through the Program tab. Each server exposes specific tools\u2014web search, file access, API calls.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">If you want to give models access to the internet, then our <a href=\"https:\/\/decrypt.co\/346185\/complete-idiots-guide-mcp-giving-your-ai-web-superpowers\" target=\"_blank\" class=\"sc-adb616fe-0 bJsyml\" rel=\"nofollow noopener\">complete guide to MCP servers<\/a> walks through the setup process, including popular options like web search and database access.<\/p>\n<p><img alt=\"\" loading=\"lazy\" width=\"1200\" height=\"780\" decoding=\"async\" data-nimg=\"1\" class=\"object-contain object-center w-full\" style=\"color:transparent\"   src=\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2025\/11\/image2.jpg@webp.webp\"\/><\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Save the file and LM Studio will automatically load the servers. When you chat with your model, it can now call these tools to fetch live data. Your local AI just gained superpowers.<\/p>\n<p>Our recommended models for 8GB systems<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">There are literally hundreds of LLMs available for you, from jack-of-all-trades options to fine-tuned models designed for specialized use cases like coding, medicine, role play or creative writing.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Best for coding: Nemotron or DeepSeek are good. They won\u2019t blow your mind, but will work fine with code generation and debugging, outperforming most alternatives in programming benchmarks. DeepSeek-Coder-V2 6.7B offers another solid option, particularly for multilingual development.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Best for general knowledge and reasoning: Qwen3 8B. The model has strong mathematical capabilities and handles complex queries effectively. Its context window accommodates longer documents without losing coherence.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Best for creative writing: DeepSeek R1 variants, but you need some heavy prompt engineering. There are also uncensored fine-tunes like the \u201cabliterated-uncensored-NEO-Imatrix\u201d <a href=\"https:\/\/huggingface.co\/DavidAU\/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf\" target=\"_blank\" rel=\"nofollow external noopener\" class=\"sc-adb616fe-0 bJsyml\">version <\/a>of OpenAI\u2019s GPT-OSS, which is good for horror; or <a href=\"https:\/\/huggingface.co\/mradermacher\/Dirty-Muse-Writer-v01-Uncensored-Erotica-NSFW-i1-GGUF\" target=\"_blank\" rel=\"nofollow external noopener\" class=\"sc-adb616fe-0 bJsyml\">Dirty-Muse-Writer<\/a>, which is good for erotica (so they say).<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Best for chatbots, role-playing, interactive fiction, customer service: Mistral 7B (especially Undi95 DPO Mistral 7B) and Llama variants with big context windows. MythoMax L2 13B maintains character traits across long conversations and adapts tone naturally. For other NSFW role-play, there are many options. You may want to check some of the models on <a href=\"https:\/\/huggingface.co\/collections\/Rikotta\/good-rp-models\" target=\"_blank\" rel=\"nofollow external noopener\" class=\"sc-adb616fe-0 bJsyml\">this list<\/a>.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">For MCP: Jan-v1-4b and Pokee Research 7b are nice models if you want to try something new. DeepSeek R1 is another good option.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">All of the models can be downloaded directly from LM Studio if you just search for their names.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">Note that the open-source LLM landscape is shifting fast. New models launch weekly, each claiming improvements. You can check them out in LM Studio, or browse through the different repositories on Hugging Face. Test options out for yourself. Bad fits become obvious quickly, thanks to awkward phrasing, repetitive patterns, and factual errors. Good models feel different. They reason. They surprise you.<\/p>\n<p class=\"font-meta-serif-pro scene:font-noto-sans scene:text-base scene:md:text-lg font-normal text-lg md:text-xl md:leading-9 tracking-px text-body gg-dark:text-neutral-100\">The technology works. The software is ready. Your computer probably already has enough power. All that&#8217;s left is trying it.<\/p>\n<p>Generally Intelligent Newsletter<\/p>\n<p>A weekly AI journey narrated by Gen, a generative AI model.<\/p>\n","protected":false},"excerpt":{"rendered":"If you\u2019re not a developer, then why in the world would you want to run an open-source AI&hellip;\n","protected":false},"author":2,"featured_media":285701,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[49,48,61],"class_list":["post-285700","post","type-post","status-publish","format-standard","has-post-thumbnail","category-technology","tag-ca","tag-canada","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/285700","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/comments?post=285700"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/285700\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media\/285701"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media?parent=285700"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/categories?post=285700"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/tags?post=285700"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}