{"slug": "nvidia-expands-nemotron-llm-family-with-hyper-efficient-models-for-agentic", "title": "Nvidia expands Nemotron LLM family with hyper-efficient models for agentic systems", "summary": "Nvidia Corp. launched the Nemotron 3.5 Super VL, a 120-billion-parameter open multimodal large language model, alongside the edge-focused Nemotron 3.5 Bolt models for agentic systems. Nvidia said Super VL matches its largest reasoning models at one-fifth the size and produces outputs nearly five times faster than other models in its class, trained on about 26 trillion tokens, 3.8 million post-training samples and reinforcement learning across 100 open environments. The Bolt 74B-A9B 24GB model activates 9 billion of its 74 billion parameters and uses 2-bit quantization to fit in 24GB of memory, while the smaller Bolt E4B 4GB model arrives later this month for GeForce RTX, Jetson and RTX/GTX Spark edge devices.", "body_md": "### Nvidia expands Nemotron LLM family with hyper-efficient models for agentic systems\n\nNvidia Corp[. today announced](https://blogs.nvidia.com/blog/nemotron-3-5-super-vl/) the launch of customizable Nemotron 3.5 Super LV large language models for always-on artificial intelligence agents and edge-focused 3.5 Bolt for local systems.\n\nThe company said the three new models will cover the full range of agent deployments, from large enterprise servers to edge devices and local hardware.\n\nNemotron 3.5 Super VL is an open 120-billion-parameter model, built in collaboration with the [Nemotron Coalition](https://nvidianews.nvidia.com/news/nvidia-launches-nemotron-coalition-of-leading-global-ai-labs-to-advance-open-frontier-models), a group of model builders and AI labs advancing open frontier-level models, designed for high-accuracy multimodal agentic tasks. It is capable of instruction following, tool use, multistep business workflows and visual understanding. Nvidia said it has comparable power to the company’s largest reasoning models at one-fifth the size.\n\nThat size, plus a new architecture, lets Super VL produce outputs nearly five times faster than other models in the same class.\n\nUnlike closed frontier models, Nvidia provides the Super VL weights in the open, meaning organizations can post-train it on their own data and deploy it on their own infrastructure. This means they can bring it behind their firewall and keep it inside their domain, maintaining sovereignty, privacy and safety.\n\nTo build Super VL, Nvidia trained the model with open data and open methods using about 26 trillion tokens across pretraining and continued pretraining. This also included 3.8 million post-training samples and reinforcement learning across 100 open environments to fine-tune the model.\n\nNvidia also said it’s releasing open datasets on Hugging Face spanning agentic tool use, finance, instruction following, long context, safety, fairness and vision-language understanding.\n\nBolt 74B-A9B 24GB is a smaller model designed to run agentic tasks locally and is based on Super VL. It uses a hybrid mixture-of-experts model that activates 9 billion of its 74 billion parameters at a time and uses 2-bit quantization to fit within 24 gigabytes of memory. This lets it run comfortably on an enterprise workstation or PC graphics processing units, so users can delegate everyday projects, including writing and debugging code, without sending workloads to the cloud.\n\nLater this month, Nvidia is also launching an even smaller model: Bolt E4B 4GB. This tiny model is built for edge deployment on GeForce RTX, Jetson and RTX/GTX Spark. This will allow physical AI and conversational agents to work within devices such as wearables, household devices, point-of-service, car dashboards, device assistants and other embedded interfaces.\n\nNvidia noted that it could be used to power interactive characters, conversational interfaces and smart user interfaces that localize or personalize.\n\n##### Image: Nvidia\n\n# A message from John Furrier, co-founder of SiliconANGLE:\n\nSupport our mission to keep content open and free by engaging with theCUBE community. **Join theCUBE’s Alumni Trust Network**, where technology leaders connect, share intelligence and create opportunities.\n\n- **15M+ viewers of theCUBE videos** , powering conversations across AI, cloud, cybersecurity and more\n- **11.4k+ theCUBE alumni** — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network\n\n### Are you an AWS customer?  Support SiliconANGLE financially by buying your AWS services from our Marketplace portal page and links: [https://siliconangle.com/aws-marketplace/](https://siliconangle.com/aws-marketplace/)\n\n##### **About SiliconANGLE Media**\n\n[SiliconANGLE](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fsiliconangle.com%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=SiliconANGLE&index=9&md5=646b1b564e2259100a2b8638aab0a552),\n\n[theCUBE Network](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fwww.thecube.net%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=theCUBE+Network&index=10&md5=7de2a85f95ab4a4a495cede20b8cb1da),\n\n[theCUBE Research](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fthecuberesearch.com%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=theCUBE+Research&index=11&md5=7bb33676722925eb57d588ec343e4f6f),\n\n[CUBE365](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fwww.cube365.net%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=CUBE365&index=12&md5=d310fb35919714e66ad8d42c9c0c1bc6),\n\n[theCUBE AI](https://cts.businesswire.com/ct/CT?id=smartlink&url=https%3A%2F%2Fwww.thecubeai.com%2F&esheet=54119777&newsitemid=20240910506833&lan=en-US&anchor=theCUBE+AI&index=13&md5=b8b98472f8071b23ebb10ab9a8dd0683)and theCUBE SuperStudios — with flagship locations in Silicon Valley and the New York Stock Exchange — SiliconANGLE Media operates at the intersection of media, technology and AI.\n\nFounded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.", "url": "https://wpnews.pro/news/nvidia-expands-nemotron-llm-family-with-hyper-efficient-models-for-agentic", "canonical_source": "https://siliconangle.com/2026/10/15/nvidia-expands-nemotron-llm-family-with-hyper-efficient-models-for-agentic-systems/", "published_at": "2026-10-15 17:10:27+00:00", "updated_at": "2026-10-15 17:24:38.847224+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-products", "generative-ai", "ai-infrastructure"], "entities": ["Nvidia Corp.", "Nemotron 3.5 Super VL", "Nemotron 3.5 Bolt", "Bolt 74B-A9B 24GB", "Bolt E4B 4GB", "Nemotron Coalition", "Hugging Face", "GeForce RTX"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/nvidia-expands-nemotron-llm-family-with-hyper-efficient-models-for-agentic", "markdown": "https://wpnews.pro/news/nvidia-expands-nemotron-llm-family-with-hyper-efficient-models-for-agentic.md", "text": "https://wpnews.pro/news/nvidia-expands-nemotron-llm-family-with-hyper-efficient-models-for-agentic.txt", "jsonld": "https://wpnews.pro/news/nvidia-expands-nemotron-llm-family-with-hyper-efficient-models-for-agentic.jsonld"}}