NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16

Checkpointnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16Model card indexedModel card

Support summary

NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 is a checkpoint published by NVIDIA, built on the NemotronHForCausalLM architecture. vLLM and TensorRT-LLM list its architecture, but not this exact checkpoint.

Configured context: 262,144 tokens
License: openmdw-1.1

Hugging Face model card

Publisher: NVIDIA
Task: text generation
License: openmdw-1.1
Library: transformers
Architecture: NemotronHForCausalLM
Weight tensor elements: 560.5B
Tensor types: BF16, F32
Configured context: 262,144 tokens
Languages: en, fr, es, it, de, pt, ja, ko, hi, ar, zh, he
Weight access: Public
Repository created: 2026-06-03

Source 1 Source 2 Source 3Reviewed 2026-09-05

Model notes and sources

Engine support

3 engines

Engine support for NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16
Engine	Release	Evidence scope	Last known supported
vLLM	`0.28.0`Newest indexed	Architecture listed; exact checkpoint unknown	No supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLang	`0.5.19`Newest indexed	No matching evidence curated	No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM	`1.2.1`Newest indexed	Architecture listed; exact checkpoint unknown	No supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1