{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2026-08-11-nvidia-nemotron-3-5-lightning/","md":"https://postcutoff.com/e/2026-08-11-nvidia-nemotron-3-5-lightning/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-08-11-nvidia-nemotron-3-5-lightning","date":"2026-08-11","date_precision":"day","short_title":"NVIDIA releases open Nemotron 3.5 Lightning and NeMo Switchyard model router","deck":null,"takeaway":"On 2026-08-11 NVIDIA released Nemotron 3.5 Lightning, an open 30B-parameter (3B active) mixture-of-experts model for long-running agentic workloads that runs on a single laptop/desktop GPU, plus NeMo Switchyard, open software that routes sub-tasks between models.","category":"open-source","category_label":"Open source","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"NVIDIA Blog - Nemotron 3.5 Lightning and NeMo Switchyard","url":"https://blogs.nvidia.com/blog/nemotron-lightning-switchyard-rtx-dgx/","type":"official","group":"primary","domain":"blogs.nvidia.com"},{"n":2,"title":"Hugging Face - NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4","url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4","type":"code","group":"primary","domain":"huggingface.co"},{"n":3,"title":"GitHub - NVIDIA-NeMo/Switchyard","url":"https://github.com/NVIDIA-NeMo/Switchyard","type":"code","group":"primary","domain":"github.com"},{"n":4,"title":"CNBC - Nvidia releases Nemotron 3.5 Lightning open-source AI model","url":"https://www.cnbc.com/2026/08/11/nvidia-releases-nemotron-3point5-lightning-open-source-ai-model-.html","type":"press","group":"press","domain":"cnbc.com"},{"n":5,"title":"Technology.org - Nvidia is building a 1-trillion-parameter open model called Nemotron 4","url":"https://www.technology.org/2026/08/12/nvidia-nemotron-4-trillion-parameter-open-model/","type":"press","group":"press","domain":"technology.org"}],"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["NVIDIA"],"title":"NVIDIA releases open Nemotron 3.5 Lightning and NeMo Switchyard model router","summary":"On 2026-08-11 NVIDIA released Nemotron 3.5 Lightning, an open 30B-parameter (3B active) mixture-of-experts model for long-running agentic workloads that runs on a single laptop/desktop GPU, plus NeMo Switchyard, open software that routes sub-tasks between models. Reports the same week said NVIDIA is training a ~1-trillion-parameter Nemotron 4.","key_facts":["Released 2026-08-11","Nemotron 3.5 Lightning: 30B-parameter MoE (Hugging Face id NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4)","NVIDIA claims up to 4x faster output and 30% faster agentic task completion vs models in its class","NeMo Switchyard routing: frontier accuracy at nearly one-third the task cost of Opus 4.8 alone (NVIDIA)","Partner results: Ramp cut costs 58% and runtime 33%; Cognition cut mean cost 28%; Boomi 100% domain-routing accuracy","Runs on RTX PCs, DGX Spark, DGX Station, Jetson; open weights, data and techniques","Reported (Aug 2026): Nemotron 4 in training, largest version at least 1 trillion parameters, possibly ready late autumn"],"key_numbers":[],"tags":["nvidia","nemotron","open-weights","moe","agents","routing","local-ai"],"science":null,"body_md":"## What happened\n\nNVIDIA shipped **Nemotron 3.5 Lightning**, an efficiency-focused open MoE model meant to serve as a fast worker inside\nmulti-agent systems, alongside **NeMo Switchyard**, which decides which model handles each part of a workflow (code\nreview, tool use, alert triage, billing questions). NVIDIA frames this as \"systems of models\" rather than one giant model.\n\n## Why it matters\n\nNVIDIA is now a significant American open-weight model developer; cheap local MoE workers plus routing directly target\nthe cost of long-running agents, which dominate 2026 inference demand.\n\n\"3B active\" is inferred from the model id suffix A3B. Nemotron 4 details are press reports, not official.","disputed":[],"related":[{"id":"2026-03-16-nvidia-gtc-2026-vera-rubin-feynman","url":"https://postcutoff.com/e/2026-03-16-nvidia-gtc-2026-vera-rubin-feynman/","date":"2026-03-16","date_precision":"day","short_title":"NVIDIA GTC 2026: Vera Rubin platform, Groq 3 LPX, Feynman preview and $1T demand outlook","deck":null,"takeaway":"It set the hardware roadmap that most frontier labs' 2026-2028 compute plans depend on, and signaled NVIDIA's push into inference-specialized silicon and agent software.","category":"hardware-compute","category_label":"Chips & compute","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["NVIDIA"]}],"people":[],"posts":[],"videos":[{"id":"nvidia-why-ai-agents-need-more-than-one-model","title":"Why AI Agents Need More Than One Model","url":"https://postcutoff.com/v/nvidia-why-ai-agents-need-more-than-one-model/"}],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":103,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":42,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":133,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":72,"in_training_data":false}],"short_url":null}