UTC

Nemotron 3 Nano 30B A3B

NVIDIA · open weights · served by 15 providers · reasoning

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

Weights
Open
Released
2025-12-15
Knowledge cutoff
2025-06-25
Context window
256K
Hugging Face repository

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 at commit 9bee19446c, last changed 2026-08-24

Licence
nvidia-nemotron-open-model-license
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.
  • Built on nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.

What the Hub's scanners report

10 weight files, 10 with a scan result. No scanner reports an issue with them.

The model at this commit, its 10 weight files with their SHA-256 and its base models.

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
  • Amazon Bedrocknvidia.nemotron-nano-3-30b
  • Cortecsnvidia-nemotron-3-nano-30b-a3b
  • Crusoenvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
  • Deep Infranvidia/Nemotron-3-Nano-30B-A3Bdeprecated
  • Eden AIdeepinfra/nvidia/Nemotron-3-Nano-30B-A3B
  • Infomaniaknvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8deprecated
  • Kilo Gatewaynvidia/nemotron-3-nano-30b-a3b
  • Merge Gatewaynvidia/nemotron-3-nano-30b-a3b
  • NanoGPTnvidia/nemotron-3-nano-30b-a3b
  • Nebius Token Factorynvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
  • Novita AInvidia/nemotron-3-nano-30b-a3b
  • Ollama Cloudnemotron-3-nano:30b
  • OpenRouternvidia/nemotron-3-nano-30b-a3b
  • Thinking Machinesnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
  • Venice AInvidia-nemotron-3-nano-30b-a3b
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.