NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

Home/Models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

kind: nvfp4
quant: nvfp4 (4-bit)
family: nemotron
modality: text-generation
root model: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
provider: nvidia
license: other
language: en, fr, es, it, de, pt, ja, ko, hi, ar, zh, he
context: 1M
library: transformers
vRAM (GB): —
size on disk: —
downloads: 260,898
likes: 263
created: —
last modified: 2026-06-24T19:23:25+00:00 (2026)
huggingface: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
tags: transformerssafetensorsnemotron_htext-generationnvidiapytorchnemotron-3latent-moemtpconversationalenfresitdeptjakohiarzhhedataset:nvidia/nemotron-post-training-v3dataset:nvidia/nemotron-pre-training-datasets

benchmark	category	score	context	conf	evidence
RULER	long-context	94.7	RULER 1M	medium	`\| RULER 1M \| 94.7 \| 94.0 \|`
GPQA	reasoning	87.0	GPQA (no tools)	medium	`\| GPQA (no tools) \| 87.0 \| 87.9 \|`
IFBench	instruction-following	81.7	IFBench (prompt)	medium	`\| IFBench (prompt) \| 81.7 \| 82.3 \|`
SWE-bench Verified	swe	70.7	SWE-Bench Verified	medium	`\| SWE-Bench Verified \| 70.7 \| 69.5 \|`
Terminal-Bench 2.1	agentic-coding	56.4	Terminal Bench 2.1	medium	`\| Terminal Bench 2.1 \| 56.4 \| 53.9 \|`
SciCode	coding	44.6	SciCode (subtask)	medium	`\| SciCode (subtask) \| 44.6 \| 43.5 \|`
BrowseComp	agentic	44.4	BrowseComp	medium	`\| BrowseComp \| 44.4 \| 41.4 \|`
Humanity's Last Exam	knowledge	26.7	HLE (no tools)	medium	`\| HLE (no tools) \| 26.7 \| 26.1 \|`
Terminal-Bench	agentic-coding	2.1		medium	`Terminal Bench 2.1`

none scraped.