UTC

Nemotron 3 Super 120B A12B

NVIDIA · open weights · served by 21 providers · tool calling, reasoning

nvidia/nemotron-3-super-120b-a12b

Weights
Open
Released
2026-03-11
Knowledge cutoff
2025-06
Context window
262K
Hugging Face repository

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 at commit 2dc98e2afe, last changed 2026-08-25

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.

What the Hub's scanners report

32 weight files, 31 with a scan result. No scanner reports an issue with them.

The model at this commit, its 32 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-super-120b-a12b-free
  • Amazon Bedrocknvidia.nemotron-super-3-120b
  • Boundlessnemotron3-super
  • Cloudflare Workers AI@cf/nvidia/nemotron-3-120b-a12bdeprecated
  • Crusoenvidia/NVIDIA-Nemotron-3-Super-120B-A12B
  • Eden AIdeepinfra/nemotron-3-super-120b-a12b
  • Eden AInebius/nvidia/nemotron-3-super-120b-a12b
  • Kenarinemotron-3-super-120b-a12b
  • Kilo Gatewaynvidia/nemotron-3-super-120b-a12b
  • NanoGPTnvidia/nemotron-3-super-120b-a12b
  • NanoGPTnvidia/nemotron-3-super-120b-a12b:thinking
  • Nebius Token Factorynvidia/nemotron-3-super-120b-a12b
  • Ollama Cloudnemotron-3-super
  • OpenCodenemotron-3-super-freedeprecated
  • OpenRouternvidia/nemotron-3-super-120b-a12b
  • Perplexity Agentnvidia/nemotron-3-super-120b-a12bdeprecated
  • Requestynvidia-nemotron-3-super-120b-a12b
  • stepping stone AGNVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B
  • Thinking Machinesnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
  • Thinking Machinesnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144
  • Vercel AI Gatewaynvidia/nemotron-3-super-120b-a12b
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.