Nemotron 3 Ultra 550B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
550B parameters, 55B active per token (512 latent experts, 22 routed), in a 108-layer stack where only 12 layers are attention, so the KV cache stays small. Includes a multi-token-prediction module for faster generation. Text only, 262,144-token context, OpenMDW-1.1. NVIDIA documents vLLM and SGLang serving on multi-GPU nodes.
Nemotron 3 Ultra 550B 在 Q4_K_M 下约需 339 GB 显存——量化权重加框架开销，不含 KV 缓存。在 Apple Silicon 上，这部分来自统一内存。
按量化级别的显存与速度
计算基准：NVIDIA RTX 4090 (24 GB)。包含 8K 上下文的 KV 缓存，因此数值高于上方的主数字。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 185.2 GB | — | 放不下 | |
| Q3_K_M 3.41 bpw | 239.8 GB | — | 放不下 | |
| Q4_K_M 4.83 bpw | 339.3 GB | — | 放不下 | |
| Q5_K_M 5.67 bpw | 398.2 GB | — | 放不下 | |
| Q6_K 6.56 bpw | 460.5 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 596.4 GB | — | 放不下 | |
| F16 16.00 bpw | 1121.9 GB | — | 放不下 |
黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型，详见 方法说明页. Nemotron 3 Ultra 550B 显存计算器 →
运行 Nemotron 3 Ultra 550B
目录中能运行 Nemotron 3 Ultra 550B 的最便宜 GPU 是 Apple M3 Ultra (512 GB).
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
如何运行 Nemotron 3 Ultra 550B
No local Ollama tag. Ollama lists nemotron-3-ultra only as a cloud-hosted ':cloud' tag, which runs on Ollama's servers, not your machine.
规格
Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.
- 参数量
- 550 Billion (55B active)
- 上下文窗口
- 262,144
- 架构
- Hybrid Mamba-2 + LatentMoE + attention, with MTP
- 提供商
- NVIDIA
- 许可证
- OpenMDW-1.1
- Availability
- Weights downloadable
- Practical deployment
- Workstation (large unified memory or pro GPU)
- 规格量化
- Q4_K_M
- 系统内存
- 512 GB
- 记录更新于
- 2026-10-13
Commercial use permitted. No usage restrictions beyond attribution.
质量与使用场景
评分由模型作者或独立评测方发布——衡量质量而非吞吐量，并非我们实测。
Independent evaluation — not vendor-claimed and not measured by us
| 基准 | 分数 | 来源 |
|---|---|---|
| AA Intelligence Index v4.3.2 (Reasoning) | 23 | independent · Artificial Analysis · snapshot 2026-10-13 |
Nemotron 3 Ultra 550B — 常见问题
How much VRAM does Nemotron 3 Ultra 550B need?
About 339 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Nemotron 3 Ultra 550B run on an RTX 4090 (24 GB)?
No. Nemotron 3 Ultra 550B needs about 339 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run Nemotron 3 Ultra 550B locally?
No local Ollama tag. Ollama lists nemotron-3-ultra only as a cloud-hosted ':cloud' tag, which runs on Ollama's servers, not your machine. Running the published tag would send your prompts to a hosted GPU rather than your own machine.