https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b Dated changes, score moves with their causes, what our workers noticed, and reviews for Nemotron 3 Ultra 550B A55B. en Wed, 21 Oct 2026 23:41:49 +0000 https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#rev_3955 https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#rev_3955 Wed, 21 Oct 2026 00:00:00 +0000 review NVIDIA merged a fix on 17 June 2026 so the NVFP4 card's SGLang command uses the nemotron_3 reasoning parser, while the BF16 card still passes nemotron_v3, a name SGLang doesn't register, and the same pull request waits there. The last change is a card edit on 24 August, and the reasoning parser last changed on 5 June. NVIDIA replied to none of 9 discussions, and there's no LICENSE file. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#rev_3956 https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#rev_3956 Wed, 21 Oct 2026 00:00:00 +0000 review NVIDIA's smallest build is NVFP4 at 352.38 GB, about 422.9 GB with a fifth added, and its card asks for 4 × B200 or 8 × H100. BF16 is 1,121.08 GB on 8 × B200 or 16 × H100. Nobody publishes an Ultra GGUF, and Ollama lists it only as a cloud model. OpenMDW-1.1 permits free commercial use. NVIDIA's API, DeepInfra and Fireworks host it, with no price in the dossier. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#rev_3957 https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#rev_3957 Wed, 21 Oct 2026 00:00:00 +0000 review The Nemotron 3 Ultra card shows a tool declared in the OpenAI schema with tool_choice and calls read back, names qwen3_coder for vLLM and SGLang, and gives the chat_template_kwargs SGLang needs to parse reasoning and calls together. Thinking turns off, or drops to medium effort, per request. Structured output is claimed from training without instructions. Of 18 independent results from four sources, Scale SEAL's MCP Atlas gives 63.1 and Vals AI's Terminal-Bench 2.1 run 50.94. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#rev_3958 https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#rev_3958 Wed, 21 Oct 2026 00:00:00 +0000 review NVIDIA's technical report says Nemotron 3 Ultra was trained, with an agentic safety teacher and a verifier, to finish the user's task while ignoring adversarial instructions hidden in tool responses aimed at write tools, exfiltration included. That is a trained instruction hierarchy between the user and tool output, though no attack rate or other safety result is published. The card's vLLM, SGLang and TensorRT-LLM commands pass trust-remote-code, and both repositories ship Python. PSIRT handles reports. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Nemotron 3 Ultra is NVIDIA's largest open-weight hybrid Mamba-2 and latent mixture-of-experts reasoning model for agents, 550B parameters with 55B active and up to 1M tokens of context, published on Hugging Face in BF16 and NVFP4 under OpenMDW-1.1.