> For the complete documentation index, see [llms.txt](https://docs.clore.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.clore.ai/guides/language-models/nemotron-3-ultra.md).

# NVIDIA Nemotron 3 Ultra (550B Mamba-MoE)

Run NVIDIA Nemotron 3 Ultra, the 550B open Mamba-MoE hybrid, on Blackwell rigs from the Clore.ai marketplace

{% hint style="info" %}
**Status (August 2026):** NVIDIA announced **Nemotron 3 Ultra** at Computex on **4 June 2026** and released it under the **OpenMDW-1.1** licence — weights, training data, recipe and the reinforcement-learning environment. **550B total / 55B active**, hybrid **Mamba-2 + MoE + attention** architecture with multi-token prediction, context up to **1M tokens**. Weights: [nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16) and an official [NVFP4 build](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4).
{% endhint %}

Two things set this release apart from the Chinese open-weight wave. First, **the licence is unusually complete**: OpenMDW-1.1 covers the model, the data and the recipe, so the whole pipeline is reproducible rather than just the checkpoint. Second, **the architecture is not a plain transformer** — interleaved Mamba-2 state-space layers with MoE and select attention layers, which is why NVIDIA quotes throughput well above what a 550B dense-attention model would give.

For Clore.ai renters there is a neat fit: the official **NVFP4** checkpoint is built for Blackwell, and the biggest rigs on the marketplace are 4× RTX PRO 6000 Blackwell (380GB).

### Key Specs

| Property        | Value                                                                      |
| --------------- | -------------------------------------------------------------------------- |
| Parameters      | 550B total, 55B active                                                     |
| Architecture    | LatentMoE — Mamba-2 + MoE + attention hybrid, MTP, 512 experts (22 active) |
| Context         | Up to 1,000,000 tokens                                                     |
| License         | OpenMDW-1.1 (model, data, recipe, RL environment)                          |
| Release Date    | 4 June 2026                                                                |
| Weights         | NVFP4 352GB · Q2\_K\_XL GGUF 202GB · Q3\_K\_M GGUF 274GB                   |
| Primary Tooling | vLLM, SGLang, TensorRT-LLM, llama.cpp                                      |

***

## Requirements

| Build          | Size    | Clore.ai rig                                         |
| -------------- | ------- | ---------------------------------------------------- |
| `UD-IQ1_M`     | 188GB   | 8× RTX 5090 (248GB)                                  |
| `UD-Q2_K_XL`   | 202GB   | 8× RTX 5090 (248GB) — 47 servers at ≥242GB           |
| `UD-Q3_K_M`    | 274GB   | 10× RTX 5090 (310GB) or 4× RTX PRO 6000 (380GB)      |
| NVFP4 official | 352GB   | 4× RTX PRO 6000 Blackwell (380GB) — 2 servers listed |
| BF16 official  | \~1.1TB | [bare metal](https://clore.ai/bare-metal)            |

{% hint style="warning" %}
**NVFP4 requires Blackwell.** The FP4 tensor cores exist on RTX 50-series and RTX PRO 6000, not on Ada or Ampere. On a 4090 or 3090 rig, use the GGUF builds instead. See [CUDA & PyTorch Compatibility](/guides/getting-started/cuda-pytorch-compatibility.md).
{% endhint %}

***

## Deploy

**NVFP4 on a Blackwell rig (vLLM):**

```bash
vllm serve nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 \
  --tensor-parallel-size 4 \
  --trust-remote-code \
  --max-model-len 262144 \
  --gpu-memory-utilization 0.90 \
  --enable-expert-parallel
```

**GGUF across an RTX 5090 rig (llama.cpp):**

```bash
huggingface-cli download unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF \
  --include "*UD-Q2_K_XL*" --local-dir /workspace/nemotron

llama-server -m /workspace/nemotron/*UD-Q2_K_XL*-00001-of-*.gguf \
  --host 0.0.0.0 --port 8080 \
  -ngl 999 --split-mode layer -c 131072 --flash-attn --no-mmap
```

Reasoning is a chat-template flag: the model emits a reasoning trace before its answer, and you can turn that off for latency-sensitive calls.

Other prebuilt checkpoints: [`RedHatAI/...-FP8-dynamic`](https://huggingface.co/RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-dynamic) and [`RedHatAI/...-quantized.w4a16`](https://huggingface.co/RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-quantized.w4a16).

***

## Clore.ai GPU Recommendations

| Setup                         | Total VRAM | Build              | Clore.ai cost   |
| ----------------------------- | ---------- | ------------------ | --------------- |
| 8× RTX 5090                   | 248GB      | Q2\_K\_XL GGUF     | \~$2.00–3.50/hr |
| 10× RTX 5090                  | 310GB      | Q3\_K\_M GGUF      | \~$5.00/hr      |
| **4× RTX PRO 6000 Blackwell** | **380GB**  | **NVFP4 official** | **\~$5.00/hr**  |

***

## Use Cases

* **Long-running agents** — NVIDIA built the RL environment for exactly this and shipped it with the weights
* **Reproducible research** — data and recipe are covered by the licence, so results can be rebuilt, not just replayed
* **High-throughput reasoning** — the Mamba hybrid decodes faster than a dense-attention model of comparable size
* **High-stakes RAG** — long context plus a reasoning trace you can inspect
* **US-jurisdiction open weights** — the strongest US-developed open-weight model of the summer, where that matters procurement-wise

***

## Troubleshooting

| Issue                             | Fix                                                                       |
| --------------------------------- | ------------------------------------------------------------------------- |
| NVFP4 fails to load               | The rig is not Blackwell — use GGUF or an FP8 build                       |
| `nemotron_h` architecture unknown | Update vLLM/SGLang/llama.cpp; the hybrid Mamba layers need recent support |
| Reasoning traces in every reply   | Turn the reasoning flag off in the chat template for short-latency calls  |
| Throughput below expectations     | Enable MTP-based speculative decoding; the model ships MTP layers         |
| OOM on 8× 5090 at Q3              | Q3\_K\_M is 274GB — you need 310GB+ of VRAM                               |

***

## Next Steps

* **Smaller sibling:** [Nemotron 3 Super](/guides/language-models/nvidia-nemotron-3-super.md) — 120B MoE, fits far smaller rigs
* **Same weight class:** [GLM-5.2](/guides/language-models/glm-5-2.md) · [MiniMax M3](/guides/language-models/minimax-m3.md) · [DeepSeek V4](/guides/language-models/deepseek-v4.md)
* **Single-card alternative:** [Qwen3.8-27B](/guides/language-models/qwen38-27b.md)
* **Serving:** [TensorRT-LLM](/guides/gpu-devops/tensorrt-llm.md) · [vLLM](/guides/language-models/vllm.md)

### Links

* [Nemotron 3 Ultra BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16) · [NVFP4](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4) · [GGUF](https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF)
* [OpenMDW-1.1 licence](https://openmdw.ai/license/1-1/)
* **Rent a GPU:** [RTX 5090](https://clore.ai/rent-5090.html) · [Marketplace](https://clore.ai/marketplace)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.clore.ai/guides/language-models/nemotron-3-ultra.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.