Source-level technical characteristic used for deployment comparison.
Source-verified model profile · 1 October 2026
NVIDIA Nemotron 3.5 Lightning 30B-A3B
NVIDIA Nemotron 3.5 Lightning 30B-A3B is an open-weight model from NVIDIA focused on customization, autonomous agents, long context and efficient server/local AI deployments. The profile separates model facts, license terms, hardware, local/self-hosted operation and EU data-residency questions.
OPEN WEIGHTSOPENMDW 1.1NORTH AMERICAEU SELF-HOSTING POSSIBLE
Direct answer
What is NVIDIA Nemotron 3.5 Lightning 30B-A3B?
NVIDIA Nemotron 3.5 Lightning 30B-A3B is a Nemotron 3.5 open-weight model published by NVIDIA. It is aimed at customization, autonomous agents, long context and efficient server/local AI deployments, with 30B total, Up to 1M; NVIDIA validates 256K on a single H100 and 1M on larger supported configurations of context and Text/code → text/code. The recorded license is OpenMDW 1.1.
The exact checkpoint, precision and runtime matter. Quantized or optimized variants can reduce memory substantially, while long context and multimodal inputs increase runtime memory.
Official model source ↗Provider origin🇺🇸 United States
RegionNorth America
Parameters30B total
Active compute3B active/token
ContextUp to 1M; NVIDIA validates 256K on a single H100 and 1M on larger supported configurations
ModalitiesText/code → text/code
LicenseOpenMDW 1.1
VerificationSource-verified · 2026-10-01
Technical profile
What matters for selection.
Source-level technical characteristic used for deployment comparison.
Source-level technical characteristic used for deployment comparison.
Source-level technical characteristic used for deployment comparison.
Source-level technical characteristic used for deployment comparison.
Hardware & runtime
Can it run locally?
High-memory workstation/server class. NVIDIA documents single H100/A100 BF16 serving and optimized NVFP4 variants for broader deployment.
NVIDIA documents vLLM and SGLang for BF16, with optimized NVFP4 checkpoints for production inference.
Do not size hardware from parameter count alone: precision, context length, KV cache, batch size and modality encoders can change the real memory envelope.
License
Commercial-use check.
The recorded license is OpenMDW 1.1. Open weights describe technical availability, not a blanket statement that every use, derivative, redistribution or hosted service is unrestricted.
For production, retain the exact license and checkpoint revision and review any separate usage policy.
Technical comparison only — not legal advice.
EU deployment lens
Origin, residency and compliance are separate.
🇺🇸 United States is the provider origin recorded for this model. It is not a statement about training-data origin or where your operational data is processed.
EU/EEA self-hosting is technically possible when weights, inference, RAG, embeddings, logging, monitoring and backups are kept on the selected infrastructure. Any external services must be assessed separately.
Self-hosting is not itself a GDPR or AI Act compliance badge.
EU deployment & data-residency guide →FAQ
Common questions.
What is NVIDIA Nemotron 3.5 Lightning 30B-A3B?
NVIDIA Nemotron 3.5 Lightning 30B-A3B is an open-weight model from NVIDIA focused on customization, autonomous agents, long context and efficient server/local AI deployments.
Can NVIDIA Nemotron 3.5 Lightning 30B-A3B run locally?
High-memory workstation/server class. NVIDIA documents single H100/A100 BF16 serving and optimized NVFP4 variants for broader deployment.
Can NVIDIA Nemotron 3.5 Lightning 30B-A3B be deployed in the EU?
Yes, technically, when the downloadable weights and complete inference/data stack are operated on EU/EEA infrastructure.
Can NVIDIA Nemotron 3.5 Lightning 30B-A3B be used commercially?
The recorded license is OpenMDW 1.1; review the exact model terms before production use.
Primary source
Verify the exact checkpoint.
Publisher documentation remains authoritative for revision-specific files, runtime settings, context behavior and license links.
NVIDIA · official model page ↗