Nemotron 3.5 Lightning 30B A3B
Hugging Face (open weights) Open weights
The catch: Text-only, and the full 1M context needs multiple GPUs (the card uses 256K on one H100).
| Access | Open weights |
|---|---|
| Free limits | Free to download and self-host; you pay only for your own compute. 30B total / 3B active (Mamba-2 + MoE + attention hybrid); up to 1M-token context, 256K on a single H100. Released 1 Aug 2026; same size class as Nemotron 3 Nano 30B-A3B. |
| Modality | text, code |
| Credit card | Not required |
| Commercial use | Allowed |
| Trains on your data | – |
| Licence or terms | OpenMDW-1.1 |
| Context window | 1,048,576 tokens |
| Model id | nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 |
| Base URL | – |
| Last checked | 8 Oct 2026 |
How to use Nemotron 3.5 Lightning 30B A3B
Download the weights and serve them yourself; the quickstart below shows one way. Licence: OpenMDW-1.1.
Quickstart
vllm serve nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 # then: curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{"model":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","messages":[{"role":"user","content":"Hello"}]}'Paste into Claude Code
I want to run the open-weight model "Nemotron 3.5 Lightning 30B A3B" (nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16) for my project. Please: 1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint). 2. Give me a minimal working setup and a test request. 3. Tell me the licence terms for commercial use. 4. If a cheaper or smaller variant would do the job, mention it.
Before you ship on it
- Text-only, and the full 1M context needs multiple GPUs (the card uses 256K on one H100).
- OpenMDW License Agreement v1.1 (linked from the model card): permission to deal in the model materials without restriction, including commercially; if you distribute it you must include the agreement and keep notices;…
- Free to run means you pay for the GPUs, the serving stack and the on-call.
Questions
Is Nemotron 3.5 Lightning 30B A3B free?
Yes. Open weights offers it as open weights, with these limits: Self-host free · OpenMDW-1.1. No credit card is needed.
Can I use Nemotron 3.5 Lightning 30B A3B commercially?
Yes, under OpenMDW-1.1. Check the current terms before you ship.
How do I start with Nemotron 3.5 Lightning 30B A3B?
Download the weights and serve them yourself; the quickstart below shows one way. Licence: OpenMDW-1.1.
Source: huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16, checked 8 Oct 2026.