What are the hardware requirements for NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash?

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash requires approximately 1.2 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Where can I download or evaluate NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash?

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash by nvidia — VRAM 1.2GB, 1024K context

Name: NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash
Author: nvidia

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash is an open-source language model by nvidia. Features: 30b LLM, VRAM: 1.2GB, Context: 1024K, License: other, LLM Explorer Score: 0.31.

Arxiv:2602.06036 Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv... Dflash Latent-moe Model optimizer Modelopt Mtp Nemotron-3.5-lightning Nvidia Qwen3 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash Parameters and Internals

LLM Name	NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash
Repository 🤗	https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash
Base Model(s)	nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4
Model Size	30b
Required VRAM	1.2 GB
Updated	2026-08-11
Maintainer	nvidia
Model Type	qwen3
Model Files	1.2 GB
Model Architecture	DFlashDraftModel
License	other
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.5.3
Vocabulary Size	131072

Rank the NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 Coder 30B A3B DFlash	256K / 0.9 GB	2645	34