NVIDIA Nemotron · General · Nemotron 3
NVIDIA Nemotron 3 Ultra 550B-A55B is a recent General release in the NVIDIA Nemotron family, certified from its immutable official source revision.
NVIDIA Nemotron 3 Ultra 550B-A55B is an official self-hostable NVIDIA release in the NVIDIA Nemotron General track. It uses MoE Transformer, carries 550B / 55B MoE, supports a verified context window of 262,144 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
NVIDIA Nemotron 3 Ultra 550B-A55B uses MoE Transformer with 550B / 55B MoE. The stored architecture profile records 64 layers, hidden width 8192, 64 attention heads and a 262,144 token context ceiling where the official configuration publishes those fields.
Only exact, source-certified variants attached to this release are shown.
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Official · NVFP4 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| NVFP4 | safetensors | 4 | Official | Runtime certified |
Use only the listed transformers runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Commercial rights are not verified, so this release is not commercially recommendable.
The full 550B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
NVIDIA Nemotron 3 Ultra 550B-A55B is published under other. The release-scoped official license link and verification date are retained with the catalogue record.
Unknown / Not Recommendable. Commercial rights are not verified, so this release is not commercially recommendable.
NVIDIA Nemotron 3 Super 120B-A12B, NVIDIA Nemotron 3.5 Lightning 30B-A3B, NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Source revision: ac6e67d70b7e8a6f10d1323aee594980c0fdb0a43eec104ffbe84e87897885ec
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Certified upstream runtime evidence is available for transformers.
The stored commercial classification is Unknown / Not Recommendable. Consult the official other terms for the final obligations.
Last verified: 2026-09-03
