{"slug": "nemotron-3-5-lightning-30b-a3b-model-by-nvidia-for-use-on-1-gpu", "title": "Nemotron-3.5-lightning-30B-a3B Model by Nvidia for use on 1 GPU", "summary": "Nvidia released the Nemotron-3.5-lightning-30B-a3B model, a 30-billion-parameter AI model with 3 billion active parameters, designed to run on a single GPU. The model is available via Nvidia's NIM API, supporting a context length of 128,000 tokens and a maximum output of 16,384 tokens, with features like reasoning and thinking enabled. It is part of Nvidia's push to provide efficient, high-performance models for enterprise AI applications.", "body_md": "Skip to main content\nExplore\nModels\nSkills\nBlueprints\nGPUs\nDocs\nSearch\n⌘K\nCtrl+K\n?\nHelp Center\nGetting Started\n1\nSet up your account\nCreate and verify your account to unlock full access to NVIDIA NIM APIs.\nCreate an Account\n2\nGenerate API Key\n3\nMake your first API call\n4\nPrototype in your environment\n5\nConnect to inference partners\nResources\nDeveloper Forums\nContact Support\nFAQs\nLogin\nnemotron-3.5-lightning-30b-a3b Model by NVIDIA | NVIDIA NIM\nnvidia\n/\nnemotron-3.5-lightning-30b-a3b\nBuild\nBuild\nPlayground\nPlayground\nModel Card\nModel Card\nAPI Reference\nPrototype\nStart building with a free API endpoint.\nPython\nLangChain\nNode\nShell\nGenerate API Key\nCopied\n\n``` python\nfrom openai import OpenAI\n\nclient = OpenAI(\n  base_url = \"https://integrate.api.nvidia.com/v1\",\n  api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n  model=\"nvidia/nemotron-3.5-lightning-30b-a3b\",\n  messages=[{\"role\":\"user\",\"content\":\"\"}],\n  temperature=1,\n  top_p=0.95,\n  max_tokens=16384,\n  extra_body={\"chat_template_kwargs\":{\"enable_thinking\":True},\"reasoning_budget\":16384},\n  stream=True\n)\n\nfor chunk in completion:\n  if not chunk.choices:\n    continue\n  reasoning = getattr(chunk.choices[0].delta, \"reasoning_content\", None)\n  if reasoning:\n    print(reasoning, end=\"\")\n  if chunk.choices[0].delta.content is not None:\n    print(chunk.choices[0].delta.content, end=\"\")\n```\n\nDeploy\nReady to scale? Choose your deployment path.\nPartner Endpoints\nSelf-Hosted Deployments\nAvailable Integrations\nDeploy this model now on your endpoint provider of choice", "url": "https://wpnews.pro/news/nemotron-3-5-lightning-30b-a3b-model-by-nvidia-for-use-on-1-gpu", "canonical_source": "https://build.nvidia.com/nvidia/nemotron-3.5-lightning-30b-a3b", "published_at": "2026-08-12 11:30:10+00:00", "updated_at": "2026-08-12 11:41:17.326514+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-infrastructure"], "entities": ["Nvidia", "Nemotron-3.5-lightning-30B-a3B", "NVIDIA NIM"], "alternates": {"html": "https://wpnews.pro/news/nemotron-3-5-lightning-30b-a3b-model-by-nvidia-for-use-on-1-gpu", "markdown": "https://wpnews.pro/news/nemotron-3-5-lightning-30b-a3b-model-by-nvidia-for-use-on-1-gpu.md", "text": "https://wpnews.pro/news/nemotron-3-5-lightning-30b-a3b-model-by-nvidia-for-use-on-1-gpu.txt", "jsonld": "https://wpnews.pro/news/nemotron-3-5-lightning-30b-a3b-model-by-nvidia-for-use-on-1-gpu.jsonld"}}