--- title: I started self-hosting LLMs and absolutely loved it description: A personal account of setting up a self-hosted LLM using Ollama on a MacBook Air M1 with 16GB RAM. The author ran DeepSeek R1's 7B parameter model inside... canonical: https://daily.dev/posts/i-started-self-hosting-llms-and-absolutely-loved-it-pygyut6fh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I started self-hosting LLMs and absolutely loved it | daily.dev og:description: A personal account of setting up a self-hosted LLM using Ollama on a MacBook Air M1 with 16GB RAM. The author ran DeepSeek R1's 7B parameter model inside... og:url: https://daily.dev/posts/i-started-self-hosting-llms-and-absolutely-loved-it-pygyut6fh og:image: https://api.daily.dev/og/posts/pYGYUt6FH.png og:image:alt: I started self-hosting LLMs and absolutely loved it og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # I started self-hosting LLMs and absolutely loved it **[XDA Developers](https://daily.dev/sources/xda-developers)** · 4 min read · 0 upvotes · 0 comments ## Summary A personal account of setting up a self-hosted LLM using Ollama on a MacBook Air M1 with 16GB RAM. The author ran DeepSeek R1's 7B parameter model inside Docker for isolation, finding the experience surprisingly smooth for a modest consumer machine. Key motivations were privacy concerns and avoiding cloud subscription costs. While local models handled everyday tasks well, limitations remain — factual accuracy issues and lack of features like web search mean cloud models like ChatGPT still have an edge for demanding use cases. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can I run DeepSeek R1 7B locally on a MacBook Air M1 with 16GB of RAM? Yes, a MacBook Air with an M1 chip and 16GB of unified memory can run DeepSeek R1's 7B parameter model through Ollama, even though the machine isn't built for heavy AI workloads. The setup is manageable and surprisingly practical for everyday queries, though it lacks the raw capability, web search, and up-to-date knowledge of cloud models like ChatGPT. _daily.dev surfaces real-world hardware experiences for developers weighing local versus cloud LLM setups._ ### What parameter size LLM can run on a Raspberry Pi? On a Raspberry Pi or other low-power hardware, expect to be limited to small models around 1.5 billion parameters, which can only handle very basic queries. This is a significant step down from the 7 billion parameter models that run reasonably well on more capable hardware like a MacBook Air with an M1 chip and 16GB of memory. _Developers scoping local AI on constrained hardware track these tradeoffs on daily.dev._ ## Similar posts on daily.dev - [I started self-hosting an LLM, and it became my favorite productivity tool](https://daily.dev/posts/i-started-self-hosting-an-llm-and-it-became-my-favorite-productivity-tool-dwib7trx9) · XDA Developers · 1 upvotes · 0 comments - [I used my local LLM to rebuild my workflow from scratch, and it was better than I expected](https://daily.dev/posts/i-used-my-local-llm-to-rebuild-my-workflow-from-scratch-and-it-was-better-than-i-expected-e05siypyp) · XDA Developers · 1 upvotes · 0 comments - [Everything you need to know about running LLMs locally](https://daily.dev/posts/everything-you-need-to-know-about-running-llms-locally-7u3awxooq) · All Things Open · 0 upvotes · 0 comments - [How to Run and Customize LLMs Locally with Ollama](https://daily.dev/posts/how-to-run-and-customize-llms-locally-with-ollama-cixkmhbqh) · freeCodeCamp · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#docker](https://daily.dev/tags/docker), [#self-hosting](https://daily.dev/tags/self-hosting), [#ollama](https://daily.dev/tags/ollama), [#deepseek](https://daily.dev/tags/deepseek) [View this post on daily.dev](https://daily.dev/posts/i-started-self-hosting-llms-and-absolutely-loved-it-pygyut6fh) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"I started self-hosting LLMs and absolutely loved it","url":"https://daily.dev/posts/i-started-self-hosting-llms-and-absolutely-loved-it-pygyut6fh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-started-self-hosting-llms-and-absolutely-loved-it-pygyut6fh"},"datePublished":"2026-07-19T13:33:07.535Z","dateModified":"2026-09-14T07:38:34.922Z","description":"A personal account of setting up a self-hosted LLM using Ollama on a MacBook Air M1 with 16GB RAM. The author ran DeepSeek R1's 7B parameter model inside...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c3b38c362bca02598ff30b359497daa5?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c3b38c362bca02598ff30b359497daa5?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-started-self-hosting-llms-and-absolutely-loved-it-pygyut6fh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,docker,self-hosting,ollama,deepseek","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"I started self-hosting LLMs and absolutely loved it"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/i-started-self-hosting-llms-and-absolutely-loved-it-pygyut6fh#faq","mainEntity":[{"@type":"Question","name":"Can I run DeepSeek R1 7B locally on a MacBook Air M1 with 16GB of RAM?","acceptedAnswer":{"@type":"Answer","text":"Yes, a MacBook Air with an M1 chip and 16GB of unified memory can run DeepSeek R1's 7B parameter model through Ollama, even though the machine isn't built for heavy AI workloads. The setup is manageable and surprisingly practical for everyday queries, though it lacks the raw capability, web search, and up-to-date knowledge of cloud models like ChatGPT. daily.dev surfaces real-world hardware experiences for developers weighing local versus cloud LLM setups."}},{"@type":"Question","name":"What parameter size LLM can run on a Raspberry Pi?","acceptedAnswer":{"@type":"Answer","text":"On a Raspberry Pi or other low-power hardware, expect to be limited to small models around 1.5 billion parameters, which can only handle very basic queries. This is a significant step down from the 7 billion parameter models that run reasonably well on more capable hardware like a MacBook Air with an M1 chip and 16GB of memory. Developers scoping local AI on constrained hardware track these tradeoffs on daily.dev."}}]} ```