--- title: “We love the world where we can use both”: How Nvidia... description: Nvidia's Joey Conway outlines a 'system of models' approach where small local models and large frontier models split workloads based on cost, latency, and... canonical: https://daily.dev/posts/we-love-the-world-where-we-can-use-both-how-nvidia-thinks-about-local-and-frontier-models-xpka13cv2 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: “We love the world where we can use both”: How Nvidia thinks about local and frontier models | daily.dev og:description: Nvidia's Joey Conway outlines a 'system of models' approach where small local models and large frontier models split workloads based on cost, latency, and... og:url: https://daily.dev/posts/we-love-the-world-where-we-can-use-both-how-nvidia-thinks-about-local-and-frontier-models-xpka13cv2 og:image: https://api.daily.dev/og/posts/XpKA13Cv2.png og:image:alt: “We love the world where we can use both”: How Nvidia thinks about local and frontier models 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. # “We love the world where we can use both”: How Nvidia thinks about local and frontier models **[The New Stack](https://daily.dev/sources/newstack)** · 4 min read · 0 upvotes · 0 comments ## Summary Nvidia's Joey Conway outlines a 'system of models' approach where small local models and large frontier models split workloads based on cost, latency, and complexity. A router sits between them, directing simple tasks to fast local models and harder tasks to cloud-based frontier models. Conway emphasizes that enterprises value control over their data as much as cost savings, and that fine-tuned open models can serve as proprietary knowledge stores. Nvidia's hardware (DGX Spark, DGX Station), inference software (Dynamo), and agent stack (NemoClaw/OpenClaw) support this hybrid architecture. A collaboration with LangChain showed Nvidia's 550B-parameter Nemotron Ultra matching top closed models at up to 10x lower cost with no retraining required. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Nvidia launches a smaller, faster Nemotron model and a router to put it to work](https://daily.dev/posts/nvidia-launches-a-smaller-faster-nemotron-model-and-a-router-to-put-it-to-work-adgtw6klw) · The New Stack · 0 upvotes · 0 comments - [Nvidia brings together AI labs to build the next generation of open base models](https://daily.dev/posts/nvidia-brings-together-ai-labs-to-build-the-next-generation-of-open-base-models-a6skrnnsz) · The New Stack · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#nvidia](https://daily.dev/tags/nvidia), [#local-ai](https://daily.dev/tags/local-ai), [#ai-inference](https://daily.dev/tags/ai-inference) [View this post on daily.dev](https://daily.dev/posts/we-love-the-world-where-we-can-use-both-how-nvidia-thinks-about-local-and-frontier-models-xpka13cv2) ```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":"“We love the world where we can use both”: How Nvidia thinks about local and frontier models","url":"https://daily.dev/posts/we-love-the-world-where-we-can-use-both-how-nvidia-thinks-about-local-and-frontier-models-xpka13cv2","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/we-love-the-world-where-we-can-use-both-how-nvidia-thinks-about-local-and-frontier-models-xpka13cv2"},"datePublished":"2026-07-23T18:19:00.764Z","dateModified":"2026-07-24T18:13:41.690Z","description":"Nvidia's Joey Conway outlines a 'system of models' approach where small local models and large frontier models split workloads based on cost, latency, and...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/118e3ed201785b68ec68d5be4e51fdb5?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/118e3ed201785b68ec68d5be4e51fdb5?_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/we-love-the-world-where-we-can-use-both-how-nvidia-thinks-about-local-and-frontier-models-xpka13cv2","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,nvidia,local-ai,ai-inference","timeRequired":"PT4M"} {"@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":"“We love the world where we can use both”: How Nvidia thinks about local and frontier models"}]} ```