--- title: How Much Does a Local LLM Actually Cost to Run? I... description: A hands-on measurement of the electricity cost to run five local LLMs on an Apple M3 Ultra Mac Studio with 96 GB unified memory, using a custom... canonical: https://daily.dev/posts/how-much-does-a-local-llm-actually-cost-to-run-i-measured-every-watt-on-apple-silicon-qqe1jgcvj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon | daily.dev og:description: A hands-on measurement of the electricity cost to run five local LLMs on an Apple M3 Ultra Mac Studio with 96 GB unified memory, using a custom... og:url: https://daily.dev/posts/how-much-does-a-local-llm-actually-cost-to-run-i-measured-every-watt-on-apple-silicon-qqe1jgcvj og:image: https://api.daily.dev/og/posts/Qqe1JgcvJ.png og:image:alt: How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon 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. # How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon **[Towards Data Science](https://daily.dev/sources/tds)** · 11 min read · 0 upvotes · 0 comments ## Summary A hands-on measurement of the electricity cost to run five local LLMs on an Apple M3 Ultra Mac Studio with 96 GB unified memory, using a custom OpenAI-compatible proxy (TokenWatt) calibrated against a wall-socket power meter at $0.31/kWh. The key finding: parameter count is a poor predictor of cost per token. A 120B mixture-of-experts model costs ~$0.109/million output tokens, while a 27B dense model costs ~$0.554 — nearly five times more — because MoE models activate only a fraction of their weights per token, dramatically reducing memory bandwidth usage and improving throughput. Real-traffic data over 30 days confirms the ordering, with the dense 27B costing roughly 10x more per token than comparable MoEs. The post also covers Apple Silicon-specific considerations: idle power overhead from keeping large models resident, the 96 GB memory ceiling, and a frank comparison with cloud API pricing. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Much Does It Actually Cost to Run a Local LLM? \(Euros per Million Tokens, Measured\)](https://daily.dev/posts/how-much-does-it-actually-cost-to-run-a-local-llm-euros-per-million-tokens-measured--0cn8ttsam) · Towards Data Science · 1 upvotes · 1 comments - [Running LLMs locally vs paying for an API: the actual math](https://daily.dev/posts/running-llms-locally-vs-paying-for-an-api-the-actual-math-nk7av4ycu) · Flavio Copes · 0 upvotes · 1 comments - [Why Your LLM Bill Is 3× What You Expected](https://daily.dev/posts/why-your-llm-bill-is-3-what-you-expected-5dsz5eo2p) · DigitalOcean Community · 0 upvotes · 0 comments - [Local LLMs vs Cloud APIs: 2026 Total Cost of Ownership Analysis](https://daily.dev/posts/local-llms-vs-cloud-apis-2026-total-cost-of-ownership-analysis-1antqpssm) · SitePoint · 1 upvotes · 0 comments - [Apple Silicon costs more than OpenRouter](https://daily.dev/posts/apple-silicon-costs-more-than-openrouter-iqamiygmx) · Hacker News · 0 upvotes · 0 comments --- Tags: [#local-ai](https://daily.dev/tags/local-ai), [#ai-inference](https://daily.dev/tags/ai-inference), [#mixture-of-experts](https://daily.dev/tags/mixture-of-experts) [View this post on daily.dev](https://daily.dev/posts/how-much-does-a-local-llm-actually-cost-to-run-i-measured-every-watt-on-apple-silicon-qqe1jgcvj) ```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":"How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon","url":"https://daily.dev/posts/how-much-does-a-local-llm-actually-cost-to-run-i-measured-every-watt-on-apple-silicon-qqe1jgcvj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-much-does-a-local-llm-actually-cost-to-run-i-measured-every-watt-on-apple-silicon-qqe1jgcvj"},"datePublished":"2026-07-28T16:49:43.031Z","dateModified":"2026-07-28T17:29:17.584Z","description":"A hands-on measurement of the electricity cost to run five local LLMs on an Apple M3 Ultra Mac Studio with 96 GB unified memory, using a custom...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bd6dc3e84a7b397c824c336b8d8aecf5?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bd6dc3e84a7b397c824c336b8d8aecf5?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Towards Data Science","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":"Towards Data Science","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tds","url":"https://daily.dev/sources/tds"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-much-does-a-local-llm-actually-cost-to-run-i-measured-every-watt-on-apple-silicon-qqe1jgcvj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"local-ai,ai-inference,mixture-of-experts","timeRequired":"PT11M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Towards Data Science","item":"https://daily.dev/sources/tds"},{"@type":"ListItem","position":3,"name":"How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon"}]} ```