--- title: Cost Of Self Hosting Llama-3 8B-Instruct | daily.dev description: The cost of self-hosting the Llama-3 8B-Instruct model is about $17 per 1M tokens when using EKS, compared to $1 per 1M tokens with ChatGPT. Self-hosting the... canonical: https://daily.dev/posts/cost-of-self-hosting-llama-3-8b-instruct-jvagcck2f twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Cost Of Self Hosting Llama-3 8B-Instruct | daily.dev og:description: The cost of self-hosting the Llama-3 8B-Instruct model is about $17 per 1M tokens when using EKS, compared to $1 per 1M tokens with ChatGPT. Self-hosting the... og:url: https://daily.dev/posts/cost-of-self-hosting-llama-3-8b-instruct-jvagcck2f og:image: https://api.daily.dev/og/posts/jVAGcck2f.png og:image:alt: Cost Of Self Hosting Llama-3 8B-Instruct 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. # Cost Of Self Hosting Llama-3 8B-Instruct **[Hacker News](https://daily.dev/sources/hn)** · 6 min read · 45 upvotes · 5 comments ## Summary The cost of self-hosting the Llama-3 8B-Instruct model is about $17 per 1M tokens when using EKS, compared to $1 per 1M tokens with ChatGPT. Self-hosting the hardware can reduce the cost to less than $0.01 per 1M tokens, but it takes about 5.5 years to break even. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@rallisf1** · 2 upvotes > Sure, but you still get better results from chatGPT or Claude with zero maintenance so the price is fair. > > Unless you mod a gaming GPU with larger/more RAM chips and run bigger or multiple models, it ain't worth self-hosting IMO. **@akashnagaraj** · 2 upvotes > Could'nt you have used a quantized model and it would have been much more faster. You can run a Llama3.1-8B quantized on 12GB ram easily and if possible use it with vLLM and you can pass ~25 prompts to the model in less than a minute. What are your thoughts on this? **@mattybilly** · 2 upvotes > This article was roasted on Hackernews for being too conservative on the costs for self-hosting. Even the AWS setup in the article was considered more expensive than it needed to be for running Llama 3 - 8B locally. Comment section quote: "LLAMA 8B on [Amazon] Bedrock is $0.40 per 1M input tokens and $0.60 per 1M output tokens." > > Check out the comments section on HK for significantly more affordable self-hosting solutions with LLMs: https://news.ycombinator.com/item?id=40681784 **@hruday95** · 1 upvotes > Wonderful comparison just to get an idea of how the entire hosting works :) **@sanjeevbhandari01** · 0 upvotes > This was really nice comparison of price. ## Similar posts on daily.dev - [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 0 upvotes · 0 comments - [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments - [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments --- Tags: [#chatgpt](https://daily.dev/tags/chatgpt), [#hardware](https://daily.dev/tags/hardware), [#llm](https://daily.dev/tags/llm), [#self-hosting](https://daily.dev/tags/self-hosting) [View this post on daily.dev](https://daily.dev/posts/cost-of-self-hosting-llama-3-8b-instruct-jvagcck2f) ```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":"Cost Of Self Hosting Llama-3 8B-Instruct","url":"https://daily.dev/posts/cost-of-self-hosting-llama-3-8b-instruct-jvagcck2f","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/cost-of-self-hosting-llama-3-8b-instruct-jvagcck2f"},"datePublished":"2024-06-14T17:41:13.725Z","dateModified":"2026-03-15T03:27:30.064Z","description":"The cost of self-hosting the Llama-3 8B-Instruct model is about $17 per 1M tokens when using EKS, compared to $1 per 1M tokens with ChatGPT. Self-hosting the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8ebc089f7c7589c45bb307dd118705f1?_a=AQAEuiZ","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8ebc089f7c7589c45bb307dd118705f1?_a=AQAEuiZ","isAccessibleForFree":true,"articleSection":"Hacker News","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":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":5,"discussionUrl":"https://daily.dev/posts/cost-of-self-hosting-llama-3-8b-instruct-jvagcck2f","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":45},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":5}],"keywords":"chatgpt,hardware,llm,self-hosting","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Cost Of Self Hosting Llama-3 8B-Instruct"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/cost-of-self-hosting-llama-3-8b-instruct-jvagcck2f","comment":[{"@type":"Comment","text":"Sure, but you still get better results from chatGPT or Claude with zero maintenance so the price is fair.\nUnless you mod a gaming GPU with larger/more RAM chips and run bigger or multiple models, it ain’t worth self-hosting IMO.","datePublished":"2024-09-07T07:52:35.117Z","url":"https://daily.dev/posts/jVAGcck2f#c-4CkIKsjVN","author":{"@type":"Person","name":"John Rallis","url":"https://daily.dev/rallisf1","image":"https://avatars.githubusercontent.com/u/8031572?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}},{"@type":"Comment","text":"Could’nt you have used a quantized model and it would have been much more faster. You can run a Llama3.1-8B quantized on 12GB ram easily and if possible use it with vLLM and you can pass ~25 prompts to the model in less than a minute. What are your thoughts on this?","datePublished":"2024-08-21T09:43:27.584Z","url":"https://daily.dev/posts/jVAGcck2f#c-W655PiUBE","author":{"@type":"Person","name":"Akash Nagaraj","url":"https://daily.dev/akashnagaraj","image":"https://lh3.googleusercontent.com/a/ACg8ocI0bEtUoDYhffIVWUhFRx35JLfg2B51sK79GqAEgxACTPKbAg=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}},{"@type":"Comment","text":"This article was roasted on Hackernews for being too conservative on the costs for self-hosting. Even the AWS setup in the article was considered more expensive than it needed to be for running Llama 3 - 8B locally. Comment section quote: “LLAMA 8B on [Amazon] Bedrock is $0.40 per 1M input tokens and $0.60 per 1M output tokens.”\nCheck out the comments section on HK for significantly more affordable self-hosting solutions with LLMs: https://news.ycombinator.com/item?id=40681784","datePublished":"2024-07-01T19:20:04.339Z","url":"https://daily.dev/posts/jVAGcck2f#c-DZ2iQVJB6","author":{"@type":"Person","name":"Matt","url":"https://daily.dev/mattybilly","image":"https://lh3.googleusercontent.com/a/ACg8ocKpfkeNYEYvY717n_imoekLDxdYskvgQrGF42j66OLwyXJDkQ=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}},{"@type":"Comment","text":"Wonderful comparison just to get an idea of how the entire hosting works :)","datePublished":"2024-06-28T05:35:49.566Z","url":"https://daily.dev/posts/jVAGcck2f#c-9jranEbEO","author":{"@type":"Person","name":"Yaswanth Jagilanka","url":"https://daily.dev/hruday95","image":"https://lh3.googleusercontent.com/a/ACg8ocKvaijVx3MwPNAEzWlUt9UwdTNUqHQch2_Zo6F2KtWr-hI8peW72g=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}},{"@type":"Comment","text":"This was really nice comparison of price.","datePublished":"2024-06-20T03:28:21.656Z","url":"https://daily.dev/posts/jVAGcck2f#c-ylqCsYWRI","author":{"@type":"Person","name":"sanjeev-bhandari01","url":"https://daily.dev/sanjeevbhandari01","image":"https://lh3.googleusercontent.com/a/ACg8ocJ9o3_4d38t9azYNq1lIqbnv7vBkaYj2nbxeKdT8Wp03DuFYGcv=s96-c"}}]} ```