UTC

Nemotron 3.5 Lightning 30B A3B

NVIDIA · open weights · served by 20 providers · tool calling, reasoning

nvidia/nemotron-3.5-lightning

Weights
Open
Released
2026-08-11
Knowledge cutoff
2025-09
Context window
262K
Hugging Face repository

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 at commit a9904d24bc, last changed 2026-08-24

Licence
openmdw-1.1
Access
Open download
Library
transformers
Formats
.safetensors
  • No model signature file is published with the weights.

What the Hub's scanners report

14 weight files, 14 with a scan result. No scanner reports an issue with them.

The model at this commit, its 14 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-3.5-lightning-free
  • InferAllnvidia/nemotron-3.5-lightning-30b-a3b
  • Kilo Gatewaynvidia/nemotron-3.5-lightning
  • Kilo Gatewaynvidia/nemotron-3.5-lightning:free
  • Merge Gatewaynvidia/nemotron-3.5-lightning-30b-a3b
  • NanoGPTnvidia/nemotron-3.5-lightning
  • NanoGPTnvidia/nemotron-3.5-lightning:thinking
  • Nebius Token Factorynvidia/Nemotron-3_5-Lightning
  • Nvidianvidia/nemotron-3.5-lightning-30b-a3b
  • OpenCodenemotron-3.5-lightning-free
  • OpenRouternvidia/nemotron-3.5-lightning
  • OpenRouternvidia/nemotron-3.5-lightning:free
  • Pioneernvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
  • Requestynemotron-3.5-lightning-30b-a3b
  • RunInfranvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
  • Thinking Machinesnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
  • Thinking Machinesnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144
  • Vercel AI Gatewaynvidia/nemotron-3.5-lightning
  • Vercel AI Gatewaynvidia/nemotron-3.5-lightning-free
  • CoreWeavenvidia/NVIDIA-Nemotron-3.5-Lightning-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.