Modelofficial release

nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark

Nemotron →Hugging Face ↗

Parameters764M (3B active)

Context1M

Input → outputtext → text

Licenseother

PrecisionBF16 · nvfp4

ArchitectureQwen3DSparkModel

ReleasedAug 5, 2026

Downloads132.2K

Based on nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

Other sizes and formats in the family

Model	Params	Precision	Downloads
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16	31.6B	BF16	32.9K
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16	31.6B	BF16	615.1K
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4nvfp4	17.8B	U8	828.9K
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlashnvfp4	663M	BF16	1.4K

Compare side by side →

This release in the news

No coverage of this exact release yet.

Recent news about Nemotron

Oct 7, 2026 · Opinion / analysis
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
Oct 6, 2026 · Research paper
Enhancing Diffusion Language Models with Autoregressive Post-Training Weights
Oct 2, 2026 · Open-source release
sgl-project/sglang v0.5.21
Oct 1, 2026 · Tutorial / explainer
Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages
Sep 30, 2026 · Open-source release
huggingface/transformers v5.18.0: Release 5.18.0
Sep 29, 2026 · Open-source release
NVIDIA/TensorRT-LLM v1.3.0rc29
Sep 19, 2026 · Open-source release
ollama/ollama v0.34.3
Aug 22, 2026 · Open-source release
sgl-project/sglang v0.5.18