UTC

Nemotron 3 Nano Omni

NVIDIA · open weights · served by 9 providers · tool calling, reasoning, image input, video input, audio input

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning

Weights
Open
Released
2026-04-28
Knowledge cutoff
Not stated
Context window
256K
Hugging Face repository

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 at commit e5e9932441, last changed 2026-08-24

Licence
nvidia-open-model-agreement
Access
Open download
Library
transformers
Formats
.safetensors
  • Loading it runs code from the repository (trust_remote_code). Read that code, and pin the commit.
  • No model signature file is published with the weights.

What the Hub's scanners report

17 weight files, 17 with a scan result. No scanner reports an issue with them.

The model at this commit, its 17 weight files with their SHA-256.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • AIHubMixnemotron-3-nano-omni-30b-a3b-reasoning-free
  • Crusoenvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B
  • Deep Infranvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoningdeprecated
  • DigitalOceannemotron-3-nano-omni
  • Kilo Gatewaynvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
  • Nvidianvidia/nemotron-3-nano-omni-30b-a3b-reasoning
  • OpenRouternvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
  • Requestynemotron-3-nano-omni-30b-a3b-reasoning
  • Vultrnemotron-3-nano-omni-30b-a3b-reasoning
Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.