--- title: Your Mac is now part of Perplexity’s AI infrastructure description: Perplexity launched Hybrid Compute, a feature for its Perplexity Computer product that shifts parts of an AI agent task between cloud models and smaller models... canonical: https://daily.dev/posts/your-mac-is-now-part-of-perplexity-s-ai-infrastructure-qqtjx5r1k twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Your Mac is now part of Perplexity’s AI infrastructure | daily.dev og:description: Perplexity launched Hybrid Compute, a feature for its Perplexity Computer product that shifts parts of an AI agent task between cloud models and smaller models... og:url: https://daily.dev/posts/your-mac-is-now-part-of-perplexity-s-ai-infrastructure-qqtjx5r1k og:image: https://api.daily.dev/og/posts/QqTjX5R1k.png og:image:alt: Your Mac is now part of Perplexity’s AI infrastructure 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. # Your Mac is now part of Perplexity’s AI infrastructure **[The New Stack](https://daily.dev/sources/newstack)** · 5 min read · 0 upvotes · 0 comments ## Summary Perplexity launched Hybrid Compute, a feature for its Perplexity Computer product that shifts parts of an AI agent task between cloud models and smaller models running locally on Apple silicon Macs. A locally-run Privacy Gate flags sensitive information like names, addresses, and account numbers so users can decide whether that portion of a task stays on-device. Local tokens are free, cutting inference costs, though local models are smaller and less capable than the cloud models. At launch, users can choose between Gemma E4B, Qwen3.6 35B-A3B, or a Perplexity-post-trained version of Qwen3.6 35B. The feature requires at least 32GB of unified memory, Apple silicon, and macOS 15, and is available to Pro and Max subscribers and enterprise customers. This approach reverses the one Perplexity used for Nvidia's DGX Spark, which starts locally and calls the cloud only with permission. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Perplexity's Hybrid Compute feature and how does it work on Mac? Hybrid Compute is a Perplexity Computer feature, launched on a Tuesday, that moves parts of an AI agent task between cloud models and smaller models running locally on Apple silicon. A locally-run Privacy Gate detects sensitive information such as names, addresses, and account numbers, letting users choose whether that portion of the task stays on the Mac instead of going to the cloud. _Developers weighing local versus cloud AI processing can follow hybrid compute approaches like this on daily.dev._ ### Which local AI models can I use with Perplexity Hybrid Compute on Mac? At launch, users can choose between Gemma E4B, Qwen3.6 35B-A3B, and a version of Qwen3.6 35B that Perplexity post-trained itself, with more models planned. Perplexity handles installation through its desktop app so users don't need to open a terminal or configure the model manually. _Anyone comparing local model options for on-device AI agents can track releases like this on daily.dev._ ### What are the hardware requirements for Perplexity's Hybrid Compute on Mac? Perplexity recommends at least 32GB of unified memory, Apple silicon, and macOS 15 to run Hybrid Compute, and the feature is available to Pro and Max subscribers as well as enterprise customers. This shows that giving an agent enough local compute for meaningful work still requires relatively high-end Mac hardware, even though smaller models can run on less powerful machines. _Developers scoping hardware needs for on-device AI agents can follow updates like this on daily.dev._ --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#privacy](https://daily.dev/tags/privacy), [#local-ai](https://daily.dev/tags/local-ai), [#perplexity](https://daily.dev/tags/perplexity) [View this post on daily.dev](https://daily.dev/posts/your-mac-is-now-part-of-perplexity-s-ai-infrastructure-qqtjx5r1k) ```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":"Your Mac is now part of Perplexity’s AI infrastructure","url":"https://daily.dev/posts/your-mac-is-now-part-of-perplexity-s-ai-infrastructure-qqtjx5r1k","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/your-mac-is-now-part-of-perplexity-s-ai-infrastructure-qqtjx5r1k"},"datePublished":"2026-09-01T19:26:41.253Z","dateModified":"2026-09-02T20:05:29.258Z","description":"Perplexity launched Hybrid Compute, a feature for its Perplexity Computer product that shifts parts of an AI agent task between cloud models and smaller models...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/738feb0a12a2076c5599b064fb752632?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/738feb0a12a2076c5599b064fb752632?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","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":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/your-mac-is-now-part-of-perplexity-s-ai-infrastructure-qqtjx5r1k","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,privacy,local-ai,perplexity","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"Your Mac is now part of Perplexity’s AI infrastructure"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/your-mac-is-now-part-of-perplexity-s-ai-infrastructure-qqtjx5r1k#faq","mainEntity":[{"@type":"Question","name":"What is Perplexity's Hybrid Compute feature and how does it work on Mac?","acceptedAnswer":{"@type":"Answer","text":"Hybrid Compute is a Perplexity Computer feature, launched on a Tuesday, that moves parts of an AI agent task between cloud models and smaller models running locally on Apple silicon. A locally-run Privacy Gate detects sensitive information such as names, addresses, and account numbers, letting users choose whether that portion of the task stays on the Mac instead of going to the cloud. Developers weighing local versus cloud AI processing can follow hybrid compute approaches like this on daily.dev."}},{"@type":"Question","name":"Which local AI models can I use with Perplexity Hybrid Compute on Mac?","acceptedAnswer":{"@type":"Answer","text":"At launch, users can choose between Gemma E4B, Qwen3.6 35B-A3B, and a version of Qwen3.6 35B that Perplexity post-trained itself, with more models planned. Perplexity handles installation through its desktop app so users don't need to open a terminal or configure the model manually. Anyone comparing local model options for on-device AI agents can track releases like this on daily.dev."}},{"@type":"Question","name":"What are the hardware requirements for Perplexity's Hybrid Compute on Mac?","acceptedAnswer":{"@type":"Answer","text":"Perplexity recommends at least 32GB of unified memory, Apple silicon, and macOS 15 to run Hybrid Compute, and the feature is available to Pro and Max subscribers as well as enterprise customers. This shows that giving an agent enough local compute for meaningful work still requires relatively high-end Mac hardware, even though smaller models can run on less powerful machines. Developers scoping hardware needs for on-device AI agents can follow updates like this on daily.dev."}}]} ```