--- title: Building a Poverty-Spec AI Cluster: Repurposing RX 580s... description: A detailed guide to building a budget multi-GPU LLM inference rig using four AMD RX 580 8GB cards sourced from crypto-mining liquidation sales for $40–$60... canonical: https://daily.dev/posts/building-a-poverty-spec-ai-cluster-repurposing-rx-580s-for-local-llms-irr6yzd7o twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Building a Poverty-Spec AI Cluster: Repurposing RX 580s for Local LLMs | daily.dev og:description: A detailed guide to building a budget multi-GPU LLM inference rig using four AMD RX 580 8GB cards sourced from crypto-mining liquidation sales for $40–$60... og:url: https://daily.dev/posts/building-a-poverty-spec-ai-cluster-repurposing-rx-580s-for-local-llms-irr6yzd7o og:image: https://api.daily.dev/og/posts/iRr6yzd7O.png og:image:alt: Building a Poverty-Spec AI Cluster: Repurposing RX 580s for Local LLMs 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. # Building a Poverty-Spec AI Cluster: Repurposing RX 580s for Local LLMs **[SitePoint](https://daily.dev/sources/sitepoint)** · 23 min read · 0 upvotes · 0 comments ## Summary A detailed guide to building a budget multi-GPU LLM inference rig using four AMD RX 580 8GB cards sourced from crypto-mining liquidation sales for $40–$60 each. The total build costs under $500 and runs quantized GGUF models via llama.cpp. Covers hardware selection and gotchas (ex-mining cards, PSU sizing, BIOS settings), two software paths—ROCm/HIP with the HSA_OVERRIDE_GFX_VERSION=8.0.3 workaround for unsupported Polaris GPUs, and the more reliable Mesa Vulkan fallback—plus compiling llama.cpp for AMD multi-GPU inference, layer splitting with --tensor-split, realistic performance benchmarks (8–15 t/s for 7B models, 2–5 t/s for 70B across four cards), undervolting tips, and an honest assessment of limitations including PCIe x1 bandwidth bottlenecks and driver fragility. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [I added a second GPU just for local AI workloads, and it cost less than upgrading my main one](https://daily.dev/posts/i-added-a-second-gpu-just-for-local-ai-workloads-and-it-cost-less-than-upgrading-my-main-one-rnty4xi8p) · XDA Developers · 0 upvotes · 0 comments --- Tags: [#llama-cpp](https://daily.dev/tags/llama-cpp), [#local-ai](https://daily.dev/tags/local-ai), [#rocm](https://daily.dev/tags/rocm), [#self-hosting](https://daily.dev/tags/self-hosting) [View this post on daily.dev](https://daily.dev/posts/building-a-poverty-spec-ai-cluster-repurposing-rx-580s-for-local-llms-irr6yzd7o) ```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":"Building a Poverty-Spec AI Cluster: Repurposing RX 580s for Local LLMs","url":"https://daily.dev/posts/building-a-poverty-spec-ai-cluster-repurposing-rx-580s-for-local-llms-irr6yzd7o","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/building-a-poverty-spec-ai-cluster-repurposing-rx-580s-for-local-llms-irr6yzd7o"},"datePublished":"2026-02-21T02:51:32.914Z","dateModified":"2026-05-14T02:12:40.042Z","description":"A detailed guide to building a budget multi-GPU LLM inference rig using four AMD RX 580 8GB cards sourced from crypto-mining liquidation sales for $40–$60...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f40f0142ef96e74e07f28c6a3fc79b73?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f40f0142ef96e74e07f28c6a3fc79b73?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"SitePoint","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":"SitePoint","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/sitepoint","url":"https://daily.dev/sources/sitepoint"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/building-a-poverty-spec-ai-cluster-repurposing-rx-580s-for-local-llms-irr6yzd7o","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llama-cpp,local-ai,rocm,self-hosting","timeRequired":"PT23M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"SitePoint","item":"https://daily.dev/sources/sitepoint"},{"@type":"ListItem","position":3,"name":"Building a Poverty-Spec AI Cluster: Repurposing RX 580s for Local LLMs"}]} ```