--- title: Nvidia launches a smaller, faster Nemotron model and a... description: Nvidia launched two new AI offerings: Nemotron 3.5 Lightning, a 30B-parameter mixture-of-experts model optimized for speed (up to 4x faster) and post-training... canonical: https://daily.dev/posts/nvidia-launches-a-smaller-faster-nemotron-model-and-a-router-to-put-it-to-work-adgtw6klw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Nvidia launches a smaller, faster Nemotron model and a router to put it to work | daily.dev og:description: Nvidia launched two new AI offerings: Nemotron 3.5 Lightning, a 30B-parameter mixture-of-experts model optimized for speed (up to 4x faster) and post-training... og:url: https://daily.dev/posts/nvidia-launches-a-smaller-faster-nemotron-model-and-a-router-to-put-it-to-work-adgtw6klw og:image: https://api.daily.dev/og/posts/ADgtW6KlW.png og:image:alt: Nvidia launches a smaller, faster Nemotron model and a router to put it to work 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. # Nvidia launches a smaller, faster Nemotron model and a router to put it to work **[The New Stack](https://daily.dev/sources/newstack)** · 4 min read · 0 upvotes · 0 comments ## Summary Nvidia launched two new AI offerings: Nemotron 3.5 Lightning, a 30B-parameter mixture-of-experts model optimized for speed (up to 4x faster) and post-training customization, and NeMo Switchyard, an open-source Rust-based model routing library. Lightning is positioned for agentic workflows where a frontier model plans and a smaller fine-tuned model executes. Early partner results show significant cost savings: LangChain achieved 74% lower costs by routing only 7% of calls to a frontier model, and Ramp cut costs 58% and runtime 33% while matching frontier performance on SWE-Bench. Switchyard integrates with existing tools like Kong, OpenRouter, and LiteLLM, letting developers define model pools and set routing policies tuned for quality, latency, and cost. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What cost savings did LangChain see using NeMo Switchyard model routing? LangChain achieved 74% lower costs across 145 multi-turn Deep Agents tasks by routing only 7% of calls to a frontier model, though with a 6% accuracy tradeoff. Ramp similarly matched frontier model performance on its internal SWE-Bench while cutting costs by 58% and runtime by 33% using a Switchyard-routed mixed-model system. _Teams weighing frontier model costs against open model trade-offs find the latest routing benchmarks on daily.dev._ ### What is Nvidia NeMo Switchyard and how does it work? NeMo Switchyard is an open-source model routing library written in Rust that lets developers define a pool of models and set routing criteria and policies — tunable for quality, latency, and cost. It integrates with existing AI gateways like Kong, OpenRouter, and LiteLLM via APIs, so it slots into existing stacks without major changes. Nvidia's internal benchmarks show a Switchyard-routed system cut task-completion costs to roughly a third of running Anthropic Opus alone. _Developers building multi-model agent pipelines track routing library developments like this on daily.dev._ ## Similar posts on daily.dev - [Nemotron 3.5 Lightning now available on AI Gateway for free](https://daily.dev/posts/nemotron-3-5-lightning-now-available-on-ai-gateway-for-free-2a3hhnsqr) · Vercel · 0 upvotes · 0 comments - [NVIDIA Nemotron 3.5 Lightning · Ollama Blog](https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur) · Ollama · 3 upvotes · 0 comments - [Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI](https://daily.dev/posts/nemotron-3-nano-4b-a-compact-hybrid-model-for-efficient-local-ai-oifexpu69) · Hugging Face · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#ai-gateway](https://daily.dev/tags/ai-gateway), [#llm](https://daily.dev/tags/llm), [#mixture-of-experts](https://daily.dev/tags/mixture-of-experts), [#nvidia](https://daily.dev/tags/nvidia) [View this post on daily.dev](https://daily.dev/posts/nvidia-launches-a-smaller-faster-nemotron-model-and-a-router-to-put-it-to-work-adgtw6klw) ```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":"Nvidia launches a smaller, faster Nemotron model and a router to put it to work","url":"https://daily.dev/posts/nvidia-launches-a-smaller-faster-nemotron-model-and-a-router-to-put-it-to-work-adgtw6klw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/nvidia-launches-a-smaller-faster-nemotron-model-and-a-router-to-put-it-to-work-adgtw6klw"},"datePublished":"2026-08-11T13:07:38.212Z","dateModified":"2026-10-15T02:17:43.680Z","description":"Nvidia launched two new AI offerings: Nemotron 3.5 Lightning, a 30B-parameter mixture-of-experts model optimized for speed (up to 4x faster) and post-training...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b85cfa4fc3b5db1883f139dab7cf3787?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b85cfa4fc3b5db1883f139dab7cf3787?_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/nvidia-launches-a-smaller-faster-nemotron-model-and-a-router-to-put-it-to-work-adgtw6klw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,ai-gateway,llm,mixture-of-experts,nvidia","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":"Nvidia launches a smaller, faster Nemotron model and a router to put it to work"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/nvidia-launches-a-smaller-faster-nemotron-model-and-a-router-to-put-it-to-work-adgtw6klw#faq","mainEntity":[{"@type":"Question","name":"What cost savings did LangChain see using NeMo Switchyard model routing?","acceptedAnswer":{"@type":"Answer","text":"LangChain achieved 74% lower costs across 145 multi-turn Deep Agents tasks by routing only 7% of calls to a frontier model, though with a 6% accuracy tradeoff. Ramp similarly matched frontier model performance on its internal SWE-Bench while cutting costs by 58% and runtime by 33% using a Switchyard-routed mixed-model system. Teams weighing frontier model costs against open model trade-offs find the latest routing benchmarks on daily.dev."}},{"@type":"Question","name":"What is Nvidia NeMo Switchyard and how does it work?","acceptedAnswer":{"@type":"Answer","text":"NeMo Switchyard is an open-source model routing library written in Rust that lets developers define a pool of models and set routing criteria and policies — tunable for quality, latency, and cost. It integrates with existing AI gateways like Kong, OpenRouter, and LiteLLM via APIs, so it slots into existing stacks without major changes. Nvidia's internal benchmarks show a Switchyard-routed system cut task-completion costs to roughly a third of running Anthropic Opus alone. Developers building multi-model agent pipelines track routing library developments like this on daily.dev."}}]} ```