--- title: NVIDIA Nemotron 3.5 Lightning · Ollama Blog | daily.dev description: NVIDIA Nemotron 3.5 Lightning is now available on Ollama, a 30-billion parameter open model (3B active) built for agentic workloads like tool calling, coding... canonical: https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: NVIDIA Nemotron 3.5 Lightning · Ollama Blog | daily.dev og:description: NVIDIA Nemotron 3.5 Lightning is now available on Ollama, a 30-billion parameter open model (3B active) built for agentic workloads like tool calling, coding... og:url: https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur og:image: https://api.daily.dev/og/posts/UY1KbA1uR.png og:image:alt: NVIDIA Nemotron 3.5 Lightning · Ollama Blog 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 Nemotron 3.5 Lightning · Ollama Blog **[Ollama](https://daily.dev/sources/ollama)** · 3 min read · 3 upvotes · 0 comments ## Summary NVIDIA Nemotron 3.5 Lightning is now available on Ollama, a 30-billion parameter open model (3B active) built for agentic workloads like tool calling, coding sub-agents, and long-running assistants that run entirely on local hardware. It uses a hybrid Mixture-of-Experts architecture, supports up to 1M token context, and offers up to 4x higher throughput and 30% faster task completion than comparable open models via speculative decoding (MTP, DFlash/DSpark). It runs on NVIDIA RTX PCs, RTX PRO workstations, DGX Spark, DGX Station, and datacenter/cloud, and integrates with Claude Code, OpenClaw, Hermes Agent, and OpenCode via simple CLI commands. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I run NVIDIA Nemotron 3.5 Lightning locally with Ollama? Install Ollama and run 'ollama run nemotron-3.5-lightning' for general chat, or launch it inside a specific harness such as 'ollama launch claude --model nemotron-3.5-lightning' for Claude Code, or with OpenClaw, Hermes Agent, and OpenCode using the equivalent launch commands. Apple silicon users can use the MLX-optimized variant 'nemotron-3.5-lightning:30b-mlx'. _daily.dev helps developers wiring new local models into their agent harnesses keep track of setup steps like these._ ### What are the specs of NVIDIA's Nemotron 3.5 Lightning model? Nemotron 3.5 Lightning is a 30 billion parameter hybrid Mixture-of-Experts model with only 3 billion active parameters per token, giving it a context length up to 1M tokens. It uses speculative decoding via multi-token prediction (MTP), DFlash, or DSpark for up to 4x higher throughput than comparable open models, and runs on NVIDIA RTX PCs, RTX PRO workstations, DGX Spark, and DGX Station. _Comparing local agentic models on throughput and context length is easier when tracking releases like this on daily.dev._ ### Why does throughput matter more than raw model size for long-running AI agents? For agents that stay running through multi-step tasks, throughput determines how many steps complete per minute, which directly affects how quickly long tasks finish. Nemotron 3.5 Lightning is designed around this tradeoff, using only 3B active parameters per token so that most agentic steps like reading a file or calling a tool run fast on local hardware rather than requiring a large datacenter model. _daily.dev keeps developers evaluating agent architectures current on tradeoffs like throughput versus model size._ ## Similar posts on daily.dev - [The Fastest Nemotron Yet: Embracing NVIDIA Nemotron 3.5 Lightning in Kilo](https://daily.dev/posts/the-fastest-nemotron-yet-embracing-nvidia-nemotron-3-5-lightning-in-kilo-wcpgec5ll) · Kilo Blog · 4 upvotes · 2 comments - [Nvidia’s best model is now live](https://daily.dev/posts/nvidia-s-best-model-is-now-live-tsagrzqp8) · 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), [#ollama](https://daily.dev/tags/ollama) [View this post on daily.dev](https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur) ```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 Nemotron 3.5 Lightning · Ollama Blog","url":"https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur"},"datePublished":"2026-08-23T12:22:20.881Z","dateModified":"2026-09-13T20:59:33.856Z","description":"NVIDIA Nemotron 3.5 Lightning is now available on Ollama, a 30-billion parameter open model (3B active) built for agentic workloads like tool calling, coding...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Ollama","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":"Ollama","logo":"https://media.daily.dev/image/upload/s--dRYYkBCj--/f_auto,q_auto/v1787487632/logos/ollama-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/ollama"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,nvidia,local-ai,ollama","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ollama","item":"https://daily.dev/sources/ollama"},{"@type":"ListItem","position":3,"name":"NVIDIA Nemotron 3.5 Lightning · Ollama Blog"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur#faq","mainEntity":[{"@type":"Question","name":"How do I run NVIDIA Nemotron 3.5 Lightning locally with Ollama?","acceptedAnswer":{"@type":"Answer","text":"Install Ollama and run 'ollama run nemotron-3.5-lightning' for general chat, or launch it inside a specific harness such as 'ollama launch claude --model nemotron-3.5-lightning' for Claude Code, or with OpenClaw, Hermes Agent, and OpenCode using the equivalent launch commands. Apple silicon users can use the MLX-optimized variant 'nemotron-3.5-lightning:30b-mlx'. daily.dev helps developers wiring new local models into their agent harnesses keep track of setup steps like these."}},{"@type":"Question","name":"What are the specs of NVIDIA's Nemotron 3.5 Lightning model?","acceptedAnswer":{"@type":"Answer","text":"Nemotron 3.5 Lightning is a 30 billion parameter hybrid Mixture-of-Experts model with only 3 billion active parameters per token, giving it a context length up to 1M tokens. It uses speculative decoding via multi-token prediction (MTP), DFlash, or DSpark for up to 4x higher throughput than comparable open models, and runs on NVIDIA RTX PCs, RTX PRO workstations, DGX Spark, and DGX Station. Comparing local agentic models on throughput and context length is easier when tracking releases like this on daily.dev."}},{"@type":"Question","name":"Why does throughput matter more than raw model size for long-running AI agents?","acceptedAnswer":{"@type":"Answer","text":"For agents that stay running through multi-step tasks, throughput determines how many steps complete per minute, which directly affects how quickly long tasks finish. Nemotron 3.5 Lightning is designed around this tradeoff, using only 3B active parameters per token so that most agentic steps like reading a file or calling a tool run fast on local hardware rather than requiring a large datacenter model. daily.dev keeps developers evaluating agent architectures current on tradeoffs like throughput versus model size."}}]} ```