Hugging Face · #575

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 is a 31.6B text-generation model on Hugging Face. Run locally: llama-cli -hf nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 or ollama run hf.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16. 25 Hugging Face likes (#575 in this directory).

Model
https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16
Author
nvidia (org)
Likes
25
Downloads (30 days)
31,102
Task
text-generation
Library
transformers
License
openmdw-1.1
Parameters
31.6B
Gated
No
Created
2026-08-05
Last modified
2026-08-11
Snapshot
2026-10-29

Run it locally.

Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.

llama.cpp

llama-cli -hf nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16

Ollama

ollama run hf.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16

These commands work when this repo, or a GGUF quant of it, publishes GGUF weights. They do not invent a quant name. For safetensors-only repos, convert with llama.cpp or use a GGUF repo on the Hub.

ShadowCode prompt.

Paste this into ShadowCode after you open Settings › Local models.

In Settings › Local models, run nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16 only if a GGUF file is available. If the Hub repo is safetensors-only, use a GGUF quant instead of guessing a filename. Ask before downloading.

Download Shadowfetch Linux — ISO, checksum and signature.

Back to Hugging Face models · Methodology