--- title: NVIDIA Nemotron 3 Ultra · Ollama Blog | daily.dev description: NVIDIA Nemotron 3 Ultra is now available on Ollama's cloud, a 550B parameter (55B active) open model designed for long-running agentic workflows such as coding... canonical: https://daily.dev/posts/nvidia-nemotron-3-ultra-ollama-blog-de1o5nkmc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: NVIDIA Nemotron 3 Ultra · Ollama Blog | daily.dev og:description: NVIDIA Nemotron 3 Ultra is now available on Ollama's cloud, a 550B parameter (55B active) open model designed for long-running agentic workflows such as coding... og:url: https://daily.dev/posts/nvidia-nemotron-3-ultra-ollama-blog-de1o5nkmc og:image: https://api.daily.dev/og/posts/DE1o5nKMc.png og:image:alt: NVIDIA Nemotron 3 Ultra · 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 Ultra · Ollama Blog **[Ollama](https://daily.dev/sources/ollama)** · 2 min read · 0 upvotes · 0 comments ## Summary NVIDIA Nemotron 3 Ultra is now available on Ollama's cloud, a 550B parameter (55B active) open model designed for long-running agentic workflows such as coding agents, deep research, and enterprise automation across hundreds of tool calls. It supports a 1M token context window and uses NVIDIA's NVFP4 4-bit format for memory efficiency and speed. Benchmarks show it leading open models in agent productivity, instruction following, and long-context tasks while cutting costs by up to 30%. It can be run via Claude Code, Hermes Agent, OpenClaw, or general chat using simple Ollama CLI commands. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is NVIDIA Nemotron 3 Ultra and what is it optimized for? Nemotron 3 Ultra is a 550 billion parameter open model from NVIDIA with 55 billion active parameters per token, built for long-running agentic workflows like coding agents, deep research, and enterprise automation spanning hundreds of tool calls. It supports a 1 million token context window and uses NVIDIA's NVFP4 4-bit floating point format for memory efficiency and speed, and is available on Ollama's cloud. _Developers evaluating open agentic models can track new releases like this one on daily.dev._ ### How do I run Nemotron 3 Ultra with Claude Code using Ollama? After downloading Ollama, launch Claude Code with the model using the command 'ollama launch claude --model nemotron-3-ultra:cloud'. Similar launch commands exist for Hermes Agent ('ollama launch hermes') and OpenClaw ('ollama launch openclaw'), or you can run general chat directly with 'ollama run nemotron-3-ultra:cloud'. _Developers wiring new open models into their coding agents can find setup details like this on daily.dev._ ### How does Nemotron 3 Ultra compare to other open models on cost and performance? Nemotron 3 Ultra leads other open models on accuracy across agent productivity, instruction following, and long-context benchmarks while also delivering leading throughput, saving up to 30% on costs compared to other leading open models. It sits in the most favorable quadrant combining high accuracy with high throughput among open models tested. _Teams comparing open model costs and throughput can follow benchmarks like these on daily.dev._ ## Similar posts on daily.dev - [NVIDIA Nemotron 3.5 Lightning · Ollama Blog](https://daily.dev/posts/nvidia-nemotron-3-5-lightning-ollama-blog-uy1kba1ur) · Ollama · 3 upvotes · 0 comments - [NVIDIA Nemotron 3 Ultra is Here – and it’s Free to Use in Kilo](https://daily.dev/posts/nvidia-nemotron-3-ultra-is-here-and-it-s-free-to-use-in-kilo-qmednaxh7) · Kilo Blog · 1 upvotes · 0 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: [#open-source](https://daily.dev/tags/open-source), [#ai-agents](https://daily.dev/tags/ai-agents), [#nvidia](https://daily.dev/tags/nvidia), [#ollama](https://daily.dev/tags/ollama) [View this post on daily.dev](https://daily.dev/posts/nvidia-nemotron-3-ultra-ollama-blog-de1o5nkmc) ```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 Ultra · Ollama Blog","url":"https://daily.dev/posts/nvidia-nemotron-3-ultra-ollama-blog-de1o5nkmc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/nvidia-nemotron-3-ultra-ollama-blog-de1o5nkmc"},"datePublished":"2026-08-23T12:23:52.535Z","dateModified":"2026-08-23T12:56:10.040Z","description":"NVIDIA Nemotron 3 Ultra is now available on Ollama's cloud, a 550B parameter (55B active) open model designed for long-running agentic workflows such as 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-ultra-ollama-blog-de1o5nkmc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"open-source,ai-agents,nvidia,ollama","timeRequired":"PT2M"} {"@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 Ultra · Ollama Blog"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/nvidia-nemotron-3-ultra-ollama-blog-de1o5nkmc#faq","mainEntity":[{"@type":"Question","name":"What is NVIDIA Nemotron 3 Ultra and what is it optimized for?","acceptedAnswer":{"@type":"Answer","text":"Nemotron 3 Ultra is a 550 billion parameter open model from NVIDIA with 55 billion active parameters per token, built for long-running agentic workflows like coding agents, deep research, and enterprise automation spanning hundreds of tool calls. It supports a 1 million token context window and uses NVIDIA's NVFP4 4-bit floating point format for memory efficiency and speed, and is available on Ollama's cloud. Developers evaluating open agentic models can track new releases like this one on daily.dev."}},{"@type":"Question","name":"How do I run Nemotron 3 Ultra with Claude Code using Ollama?","acceptedAnswer":{"@type":"Answer","text":"After downloading Ollama, launch Claude Code with the model using the command 'ollama launch claude --model nemotron-3-ultra:cloud'. Similar launch commands exist for Hermes Agent ('ollama launch hermes') and OpenClaw ('ollama launch openclaw'), or you can run general chat directly with 'ollama run nemotron-3-ultra:cloud'. Developers wiring new open models into their coding agents can find setup details like this on daily.dev."}},{"@type":"Question","name":"How does Nemotron 3 Ultra compare to other open models on cost and performance?","acceptedAnswer":{"@type":"Answer","text":"Nemotron 3 Ultra leads other open models on accuracy across agent productivity, instruction following, and long-context benchmarks while also delivering leading throughput, saving up to 30% on costs compared to other leading open models. It sits in the most favorable quadrant combining high accuracy with high throughput among open models tested. Teams comparing open model costs and throughput can follow benchmarks like these on daily.dev."}}]} ```