Nemotron 3.5 Lightning

By Canonical IoT Labs Verified account

View on Snapcraft.io
Version2.0.0-beta.12+521d6fe
Revision5
Size7.1 MB
Licenseunset
Confinementstrict
Basecore24

Local AI with Nemotron 3.5 Lightning inference snap


NVIDIA Nemotron 3.5 Lightning is a customizable open model built for fast, always-on agents that run anywhere, from edge devices to local systems, datacenters, and the cloud.

Use this snap to quickly install an optimized environment for local inference with Nemotron 3.5 Lightning.

The snap includes the following hardware-optimized inference engines:

  • cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
  • nvidia-gpu: CUDA-enabled GPU acceleration

The most suitable engine is automatically selected based on the available hardware.

Install:

sudo snap install nemotron-3-5-lightning

Run:

nemotron-3-5-lightning

Some accelerators require extra drivers to be usable with this snap: https://documentation.ubuntu.com/inference-snaps/how-to/setup/drivers/

License:

The Nemotron 3.5 Lightning model is provided by NVIDIA Corporation under the NVIDIA Open Model License: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/

The licenses of all the bundled software can be found after installing the snap at /snap/nemotron-3-5-lightning/current/usr/share/doc.

Update History

2.0.0-beta.12+521d6fe (5)
11 Aug 2026, 13:45 UTC

Published5 Aug 2026, 09:43 UTC

Last updated10 Aug 2026, 22:27 UTC

First seen11 Aug 2026, 13:45 UTC