{"id":3571,"date":"2025-01-08T23:59:00","date_gmt":"2025-01-08T10:59:00","guid":{"rendered":"https:\/\/www.talkcrypto.org\/blog\/?p=3571"},"modified":"2025-02-16T00:13:31","modified_gmt":"2025-02-15T11:13:31","slug":"ollama-for-beginners","status":"publish","type":"post","link":"https:\/\/www.talkcrypto.org\/blog\/2025\/01\/08\/ollama-for-beginners\/","title":{"rendered":"Ollama for beginners"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Ollama is a free tool that allows you to runs LLMs (Large Language Models) directly on your local machine. This is convenient for AI developers, researchers, or just experimenting and learning about AI.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">There is a lot to grasp initially so the best thing to do is just to jump in, set it up and use it. Then ask questions along the way. <\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Download Ollama<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Firstly, let&#8217;s download Ollama at: <a href=\"https:\/\/ollama.com\/download\">https:\/\/ollama.com\/download<\/a> for your specific OS and then install it. When installed, you won&#8217;t see anything. It just runs in the background. To interact with it, you&#8217;ll have to use the command line.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Interacting with Ollama<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Once Ollama is installed, open your terminal and type <code>ollama --version<\/code>. Here you can see I&#8217;m running 0.5.11<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img decoding=\"async\" width=\"328\" height=\"36\" src=\"https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/02\/image.png\" alt=\"\" class=\"wp-image-3572\" srcset=\"https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/02\/image.png 328w, https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/02\/image-300x33.png 300w\" sizes=\"(max-width: 328px) 100vw, 328px\" \/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Let&#8217;s get familiar with some basic commands. Type <code>ollama --help<\/code> to show some basic commands such as: <\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama --help\nLarge language model runner\n\nUsage:\n  ollama &#91;flags]\n  ollama &#91;command]\n\nAvailable Commands:\n  serve       Start ollama\n  create      Create a model from a Modelfile\n  show        Show information for a model\n  run         Run a model\n  stop        Stop a running model\n  pull        Pull a model from a registry\n  push        Push a model to a registry\n  list        List models\n  ps          List running models\n  cp          Copy a model\n  rm          Remove a model\n  help        Help about any command\n\nFlags:\n  -h, --help      help for ollama\n  -v, --version   Show version information<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">These command are self explanatory once you&#8217;ve run it a few times but for first timers, let&#8217;s go through some examples.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">ollama serve<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">This starts your Ollama app via command line. If you have the &#8220;GUI&#8221; application though, you can run that and not have to run the serve command. Also, if you run other commands such as <code>ollama list<\/code>, the Ollama &#8220;GUI&#8221; application will start automatically. All this is to say that you probably don&#8217;t have to run <code>ollama serve<\/code>. <\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama serve\n2025\/02\/15 21:32:18 routes.go:1186: INFO server config env=\"map&#91;HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http:\/\/127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:\/Users\/seandotau\/.ollama\/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:&#91;http:\/\/localhost https:\/\/localhost http:\/\/localhost:* https:\/\/localhost:* http:\/\/127.0.0.1 https:\/\/127.0.0.1 http:\/\/127.0.0.1:* https:\/\/127.0.0.1:* http:\/\/0.0.0.0 https:\/\/0.0.0.0 http:\/\/0.0.0.0:* https:\/\/0.0.0.0:* app:\/\/* file:\/\/* tauri:\/\/* vscode-webview:\/\/*] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]\"\ntime=2025-02-15T21:32:18.285+11:00 level=INFO source=images.go:432 msg=\"total blobs: 6\"\ntime=2025-02-15T21:32:18.285+11:00 level=INFO source=images.go:439 msg=\"total unused blobs removed: 0\"\ntime=2025-02-15T21:32:18.286+11:00 level=INFO source=routes.go:1237 msg=\"Listening on 127.0.0.1:11434 (version 0.5.11)\"\ntime=2025-02-15T21:32:18.335+11:00 level=INFO source=types.go:130 msg=\"inference compute\" id=0 library=metal variant=\"\" compute=\"\" driver=0.0 name=\"\" total=\"21.3 GiB\" available=\"21.3 GiB\"\n\n&#91;GIN] 2025\/02\/15 - 21:32:43 | 200 |      66.833\u00b5s |       127.0.0.1 | HEAD     \"\/\"\n&#91;GIN] 2025\/02\/15 - 21:32:43 | 200 |    1.078416ms |       127.0.0.1 | GET      \"\/api\/tags\"\n&#91;GIN] 2025\/02\/15 - 21:32:57 | 200 |      28.167\u00b5s |       127.0.0.1 | HEAD     \"\/\"<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">ollama list<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">This will list the models you have downloaded. It will show blank for now so let&#8217;s download a model.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama list<br>NAME ID SIZE MODIFIED<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">ollama pull<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">To download a model we need to run <code>ollama pull<\/code>, but we need to know what model to pull. This is where: <a href=\"https:\/\/ollama.com\/search\">https:\/\/ollama.com\/search<\/a> comes into play. It lists all the model options available but how do you choose? <\/p>\n\n\n\n<h5 class=\"wp-block-heading\">model summary<\/h5>\n\n\n\n<p class=\"wp-block-paragraph\">Llama: Llama is an NLP (Natural Language Processing) model for tasks like text generation, summarization, and machine translation. It is ideal for general-purpose chat, conversational AI, and answering questions.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Mistral: Mistral, similar to Llama, handles code generation and large-scale data analysis, making it ideal for developers working on AI-driven coding platforms<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Phi-4: An AI language model developed by Microsoft, is a <a href=\"https:\/\/techcommunity.microsoft.com\/blog\/aiplatformblog\/introducing-phi-4-microsoft%E2%80%99s-newest-small-language-model-specializing-in-comple\/4357090\">14B parameter state-of-the-art small language model (SLM) that excels at complex reasoning in areas such as math, in addition to conventional language processing.<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">LLaVa: LLaVA is a multimodal model capable of processing text and images. (A multimodal model is an AI system that can process and understand multiple types of information or &#8220;modes&#8221; &#8211; such as text, images, audio, and video &#8211; often simultaneously.)<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Code Llama: A large language model that can use text prompts to generate and discuss code.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">These are just but a small snippet of what is available. What you&#8217;ll also notice are model size options. eg for llama3.2, there is a 1 billion or 3 billion parameter size option. The more parameters, the more accurate the model, but the larger the model size. Eg pulling Llama 3.2:1b will take 1.3Gb but Llama 3.2:3b will take 2Gb. Compare this to Llama 3.1:140b which will take a whopping 243Gb of disk space. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">So now we know about types of models and model sizes, let&#8217;s pull Llama3.2 which is simple and lightweight. Run <code>ollama pull llama3.2<\/code>. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Notice I didn&#8217;t add the model parameter? If it is left out, then it will default to <code>ollama pull llama3.2:latest<\/code> which currently is the equivalent of <code>ollama pull llama3.2:3b<\/code>. <\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama pull llama3.2\npulling manifest\npulling dde5aa3fc5ff... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f 2.0 GB\npulling 966de95ca8a6... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f 1.4 KB\npulling fcc5a6bec9da... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f 7.7 KB\npulling a70ff7e570d9... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f 6.0 KB\npulling 56bb8bd477a5... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f   96 B\npulling 34bb5ab01051... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f  561 B\nverifying sha256 digest\nwriting manifest\nsuccess<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">ollama show<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">Now if you run <code>ollama list<\/code> you should see the model you just pulled. <\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama list<br>NAME ID SIZE MODIFIED<br>llama3.2:3b a80c4f17acd5 2.0 GB 28 seconds ago<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">What is neat is that you can also show the information of this model by running <code>ollama show llama3.2<\/code><\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama show llama3.2\n  Model\n    architecture        llama\n    parameters          3.2B\n    context length      131072\n    embedding length    3072\n    quantization        Q4_K_M\n\n  Parameters\n    stop    \"&lt;|start_header_id|>\"\n    stop    \"&lt;|end_header_id|>\"\n    stop    \"&lt;|eot_id|>\"\n\n  License\n    LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n    Llama 3.2 Version Release Date: September 25, 2024<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\">ollama rm<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">To remove a model, run <code>ollama rm llama3.2<\/code> for instance. Tip: If you interrupted a download, you&#8217;ll have partial files in your \/User\/seandotau\/.ollama\/models\/blob directory so you&#8217;ll have to go there and delete it manually. <\/p>\n\n\n\n<h4 class=\"wp-block-heading\">ollama push, create, cp<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">These commands here you probably won&#8217;t be using much unless you will be creating models, copying models or pushing it to the model registry for others to use. <\/p>\n\n\n\n<h4 class=\"wp-block-heading\">ollama run<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">Now comes the moment of truth. Running the model and giving it a test drive. When you run the model, you can start interacting with it. <\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama run llama3.2\n>>> what is the capital of Germany?\nThe capital of Germany is Berlin.\n\n>>> Send a message (\/? for help)<\/code><\/pre>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><\/blockquote>\n<\/blockquote>\n\n\n\n<p class=\"wp-block-paragraph\">Cool right? To exit, type \/bye<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Extra cool features<\/h2>\n\n\n\n<h4 class=\"wp-block-heading\">Asking AI to summarise some text<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama run llama3.2 \"summarise this file in 100 words: $(cat hobbit.text )\"\nHere is a 100-word summary of the file:\n\nThe Hobbit, written by J.R.R. Tolkien in 1937, is a classic children's fantasy novel that has sold over 100\nmillion copies worldwide. The story follows Bilbo Baggins, a hobbit who joins Gandalf and dwarves on a quest to\nreclaim their treasure from the dragon Smaug. The book features themes of personal growth, heroism, and warfare,\ndrawing from Tolkien's experiences in World War I and his scholarly knowledge of Germanic philology and\nmythology. Adaptations for stage, screen, radio, board games, and video games have received critical\nrecognition, cementing its legacy as a beloved children's fantasy novel.<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">Make sure that the text file is in the current directory you are in.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">Asking AI to interpret a picture<\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">What you&#8217;ll notice here is that ollama will pull the model specified first (as I didn&#8217;t already have it) and then run it. <\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>seandotau@aseandotaus-MBP ~ % ollama run llava \"What's in this image? \/Users\/seandotau\/image.png\"\npulling manifest\npulling 170370233dd5... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f 4.1 GB\npulling 72d6f08a42f6... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f 624 MB\npulling 43070e2d4e53... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f  11 KB\npulling c43332387573... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f   67 B\npulling ed11eda7790d... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f   30 B\npulling 7c658f9561e5... 100% \u2595\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u258f  564 B\nverifying sha256 digest\nwriting manifest\nsuccess\nAdded image '\/Users\/seandotau\/image.png'\n The image features Pikachu, a popular Pok\u00e9mon character from the franchise. It is a small electric mouse with\nyellow fur, large ears, and big round eyes. Pikachu is standing upright on its hind legs, and it appears to be\nlooking directly at the camera.<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">FYI: this was the image. <\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img fetchpriority=\"high\" decoding=\"async\" width=\"980\" height=\"980\" src=\"https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/02\/image-2.png\" alt=\"\" class=\"wp-image-3574\" style=\"width:254px;height:auto\" srcset=\"https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/02\/image-2.png 980w, https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/02\/image-2-300x300.png 300w, https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/02\/image-2-150x150.png 150w, https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/02\/image-2-768x768.png 768w\" sizes=\"(max-width: 980px) 100vw, 980px\" \/><\/figure>\n\n\n\n<h4 class=\"wp-block-heading\">Using curl<\/h4>\n\n\n\n<pre class=\"wp-block-code\"><code>curl http:\/\/localhost:11434\/api\/generate -d '{\n  \"model\": \"llama3.2\",\n  \"prompt\":\"Why is the sky blue?\"\n}'<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">Note that the Ollama API returns streaming JSON responses by default, with each response being a separate JSON object on a new line. This is known as JSON Lines (JSONL) format. If you want to see the complete response in a more readable format, you can pipe the output through <code>jq<\/code> to extract just the response content:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>curl http:\/\/localhost:11434\/api\/generate \\<br>-H 'Content-Type: application\/json' \\<br>-d '{\"model\": \"llama3.2\", \"prompt\": \"Why is the sky blue?\"}' \\<br>| jq -r '.response'<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\">The streaming behavior is by design &#8211; it allows the API to send partial responses as they&#8217;re generated, rather than waiting for the complete response. If you need to disable streaming, you can add <code>\"stream\": false<\/code> to your JSON request:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>curl http:\/\/localhost:11434\/api\/generate \\<br>-H 'Content-Type: application\/json' \\<br>-d '{\"model\": \"llama3.2\", \"prompt\": \"Why is the sky blue?\", \"stream\": false}'<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Ollama is a free tool that allows you to runs<\/p>\n","protected":false},"author":1,"featured_media":3576,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[50],"tags":[],"class_list":["post-3571","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai"],"featured_image_urls":{"full":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama.png",1135,584,false],"thumbnail":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama-150x150.png",150,150,true],"medium":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama-300x154.png",300,154,true],"medium_large":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama-768x395.png",640,329,true],"large":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama-1024x527.png",640,329,true],"1536x1536":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama.png",1135,584,false],"2048x2048":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama.png",1135,584,false],"chromenews-featured":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama-1024x527.png",1024,527,true],"chromenews-large":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama-825x575.png",825,575,true],"chromenews-medium":["https:\/\/www.talkcrypto.org\/blog\/wp-content\/uploads\/2025\/01\/ollama-590x410.png",590,410,true]},"author_info":{"info":["seandotau"]},"category_info":"<a href=\"https:\/\/www.talkcrypto.org\/blog\/category\/ai\/\" rel=\"category tag\">AI<\/a>","tag_info":"AI","comment_count":"0","_links":{"self":[{"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/posts\/3571","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/comments?post=3571"}],"version-history":[{"count":2,"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/posts\/3571\/revisions"}],"predecessor-version":[{"id":3578,"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/posts\/3571\/revisions\/3578"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/media\/3576"}],"wp:attachment":[{"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/media?parent=3571"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/categories?post=3571"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.talkcrypto.org\/blog\/wp-json\/wp\/v2\/tags?post=3571"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}