{"slug": "unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4", "title": "unsloth/nvidia-nemotron-3-ultra-550b-a55b-nvfp4", "summary": "NVIDIA released the Nemotron-3-Ultra-550B-A55B-NVFP4 model, a 550-billion-parameter large language model with 55 billion active parameters using NVFP4 quantization, under the OpenMDW-1.1 license. The model, hosted externally on ModelScope and indexed by Hugging Bay, requires multi-GPU or high-RAM hardware and is pending safety and license review.", "body_md": "# unsloth/nvidia-nemotron-3-ultra-550b-a55b-nvfp4\n\nunsloth/nvidia-nemotron-3-ultra-550b-a55b-nvfp4: NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 License: openmdw-1.1. external modelscope metadata. Scan: pending.\n\n- License\n- openmdw-1.1\n- Size\n- 328.2 GB\n- Demand\n- 208 upstream downloads\n- Trust\n- Needs review 0/100\n- Trusted download\n- External or needs review\n- Run fit\n- Large hardware fit: Multi-GPU, high-RAM machine, or hosted inference\n- Files\n- 0 hosted / 0 total\n- Scan status\n- pending\n- Hosting status\n- external\n- Upstream\n- unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4\n- Declared license\n- openmdw-1.1\n- Pipeline\n- text-generation\n- Library\n- pytorch\n- Task categories\n- text-generation\n\n## About this artifact\n\nExternal ModelScope model metadata for unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4. Related arXiv: . Model files stay upstream; Hugging Bay indexes this metadata for discovery and provenance only.\n\n## Trusted download\n\nExternal or needs review. No Hugging Bay hosted download is available until source, license, and safety checks pass.\n\n- Hosted files\n- 0 of 0\n- Reviewed peer-assisted fallbacks\n- 0\n- Download plan\n[Download-plan JSON](/api/artifacts/modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4/download-plan)- Trust bundle\n[Trust-bundle JSON](/api/trust-bundles/modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4)- Review summary\n[Review-summary JSON](/api/artifacts/modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4/review-summary)- Distribution\n[Reviewed peer-fallback JSON](/api/artifacts/modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4/distribution)\n\n## Can I run this?\n\nLarge hardware fit. Multi-GPU, high-RAM machine, or hosted inference. Use compare pages to find smaller verified alternatives or request a quantized mirror if one is not hosted yet.\n\n- Estimated footprint\n- 328.2 GB\n- Suggested runners\n- Transformers, vLLM\n- Runtime files\n- 0\n- Local kit\n[Local run kit](/local-kit/modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4)\n\nRun-fit warnings: No runtime weight file is indexed yet.; Hugging Bay is showing metadata only until reviewed hosted files exist.\n\n- License: fail - openmdw-1.1\n- Provenance: pass - unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4\n- Scan: warn - pending\n- Hosted files: warn - external metadata only\n- Signed manifest: fail - not final yet\n- Community: warn - no reviews yet\n- Benchmarks: warn - no benchmark evidence\n\n## Machine-readable card\n\n[Open interactive artifact page](/#/artifact/modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4)", "url": "https://wpnews.pro/news/unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4", "canonical_source": "https://huggingbay.xyz/artifact/modelscope-unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4", "published_at": "2026-07-03 16:21:30+00:00", "updated_at": "2026-07-11 02:43:50.284627+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-infrastructure", "ai-products"], "entities": ["NVIDIA", "Nemotron-3-Ultra-550B-A55B-NVFP4", "Hugging Bay", "ModelScope", "unsloth"], "alternates": {"html": "https://wpnews.pro/news/unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4", "markdown": "https://wpnews.pro/news/unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4.md", "text": "https://wpnews.pro/news/unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4.txt", "jsonld": "https://wpnews.pro/news/unsloth-nvidia-nemotron-3-ultra-550b-a55b-nvfp4.jsonld"}}