Nemotron 3.5 Lightning 30B-A3B

In non-nerd speak

Who makes it: NVIDIA. The files come from the maker's own Hugging Face account.

License: OpenMDW License 1.1. A Linux Foundation model license. You can use, change, and share it, even to make money. Keep the license and notices when you share it.

Business use: Yes. Business use is allowed. Keep the license and notices when you share it.

Training data: We have not found a full public data release. Not yet checked in depth.

Will it say no?

Middle. NVIDIA's card and safety.md say it was trained with safety data, filtered harmful data with a guard model, and warn against removing its safety guardrails.

This comes from what the maker wrote, checked Oct 16, 2026. We have not run our own tests yet. It sits next to the trust score and does not change it. How we pick these labels.

Will it run on my computer?

Pick a computer with at least 32 GB of memory. On a Mac, that is the unified memory. On a PC, a graphics card with that much VRAM is fastest. A PC with only normal RAM will also work, just slower. This model uses a mix of experts. Only part of it works on each word, so it runs faster than its size suggests.

NVIDIA says it runs in 80 GB of memory (source). Our estimate is about 24 GB. So 80 GB machines will be a tight fit. Close the 40 browser tabs first.

Not sure? Use our pick-by-computer guide.

How to run it in LM Studio

1. Get LM Studio from lmstudio.ai and open it.
2. Open the Discover tab. Search for ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF.
3. Pick a file that ends in Q4_K_M. It is the best mix of size and quality for most people.
4. Click Download. When it is done, open a new chat and load the model.

The files are GGUF builds that LM Studio can load. We checked that this repo exists on Oct 16, 2026. Full LM Studio guide.

How to use it with Hermes

Does it fit? Yes. Its memory window is big enough for Hermes.

1. Load the model in LM Studio. Set the context length to at least 64000.
2. In LM Studio, open the Developer tab and start the server.
3. In a terminal, run hermes model. Choose LM Studio and press Enter to keep http://localhost:1234/v1.
4. Pick this model from the list. Then run hermes to start.

Steps based on the Hermes docs. Full Hermes guide.

Common questions

Is Nemotron 3.5 Lightning 30B-A3B truly open source?

No, open weights with custom rules. A Linux Foundation model license. You can use, change, and share it, even to make money. Keep the license and notices when you share it.

Can I use Nemotron 3.5 Lightning 30B-A3B for my business?

Yes. Business use is allowed. Keep the license and notices when you share it.

Do I need to sign up to download Nemotron 3.5 Lightning 30B-A3B?

No. Download without an account.

How much memory does Nemotron 3.5 Lightning 30B-A3B need?

NVIDIA says it runs within 80 GB of memory. Our estimate is about 24 GB of RAM for a 4-bit file of about 18.0 GB. This is a rough guide, not a test. So a 80 GB machine will be a tight fit.

Similar models to compare

Same maker first, then models that need about the same memory.

Where Nemotron 3.5 Lightning 30B-A3B shows up

• Best local AI for business use
• Other models that fit a 32 GB computer
• What its license means

Change history

• Oct 16, 2026 New model Nemotron 3.5 Lightning 30B-A3B: Added NVIDIA's Nemotron 3.5 Lightning 30B-A3B. 30 billion parameters with 3 billion active. NVIDIA says it runs on one 80 GB GPU at full precision. OpenMDW 1.1 license; business use allowed.

All changes on the site

Sources we checked

If the maker's page and this page disagree, trust the maker. Tell us what we got wrong.