Home / Models / Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

NVIDIA · FIELD-VERIFIED

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

Name: Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 verified model record
License: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/

Checked against the listed Hugging Face source repository on 2026-10-02. Unknown values are left explicit rather than inferred.

Source repository ↗Compare this model →History & diff →Field-verified 2026-10-02Machine-readable JSON ↗

DeveloperNVIDIA

Parameters18.3263B

Context262,144 tokens

Weight files4

Licensenvidia-open-model-agreement

Accesspublic

Evidence statusSource-first verified

Repository revision checked2026-10-02

Full field verification2026-10-02

Source policy →Methodology →

01 · WEIGHTS

Exact repository artifacts

Statusverified-available

Accesspublic

Repositorynvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

Recognized weight files4

Show all 4 exact weight files

HF API file listing ↗

02 · LICENSE

License & commercial use

Declared licensenvidia-open-model-agreement

License IDother

Commercial useCommercially usable subject to NVIDIA license conditions

Repository license filesNone observed

Classification describes the checked license terms; it is not legal advice.

License / model-card evidence ↗

03 · HARDWARE

Weight-memory estimate

BF16 / FP16~36.6 GB

FP8 / INT8~18.3 GB

INT4~9.2 GB

Weight-only decimal-GB estimate from total parameter count; excludes KV cache, activations, runtime overhead, optimizer state and sharding.

04 · FORMATS

Formats & precision evidence

Safetensors

BF16: observedFP16: not observedFP8: observedINT8: not observedINT4: not observedGGUF: not observed

“Not observed” means no matching repository artifact/name/dtype signal was found; it does not prove no third-party conversion exists.

05 · LINEAGE

Base model & family

FamilyNemotron-3-Nano-Omni

VariantNemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

Declared base modelnvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

RelationNot declared

06 · TRAINING ASSETS

Recipe & data disclosure

Training recipetraining-described-in-model-card

Data disclosurenvidia/Nemotron-Image-Training-v3

EvaluationsNot classified by automated verifier

Intermediate checkpointsNot classified by automated verifier

07 · RUNTIME SUPPORT

Declared and mentioned runtimes

Declared libraryTransformers

Declared/taggedTransformers

Mentioned in model cardNeMo, Ollama, SGLang, TensorRT-LLM, llama.cpp, vLLM

Artifact signalsNone

Tested by Open Model WeightsNo — source-derived support only

Open Model Weights does not claim runtime compatibility unless it is declared, tagged, mentioned by the publisher, or evidenced by an artifact. No inference benchmark is implied.

08 · SOURCES