NE

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash

NemotronGGUF by magnitudedevUpdated 2026-10-06
Download on Hugging Face
Parameters833M
Context1024K
Layers6
Architecturedflash
Smallest quant1.2 GB
Quick answer

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash needs about 1.7 GB of memory at its main file (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.2 GB.

NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash – DFlash speculative decoding checkpoint

The NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash model is a DFlash speculative decoding checkpoint for the Nemotron-3.5-Lightning-30B-A3B family. It is a hybrid LatentMoE language model designed for reasoning, chat, and agentic workflows. The model supports up to 1M token context and is intended for lower‑latency speculative decoding on data centre GPUs and high‑end local GPU systems.

Good at

  • Reasoning and chat
  • Agentic workflows
  • Low‑latency speculative decoding

Limits

  • No vision support
  • Requires NVFP4 quantization
  • License governed by OpenMDW‑1.1

Best for

  • Deploying on high‑end GPUs
  • Serving large context workloads
  • Integrating with DFlash‑assisted serving

Who it’s for. Developers who need a dense GQA model with speculative decoding for reasoning, chat, RAG, and agentic tasks on data centre or workstation GPUs. The model is suitable for commercial or non‑commercial use under the OpenMDW‑1.1 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.2 GB 1.7 GB
Fits Get file →

The only available quant is NVFP4. The GGUF file is 1.19 GB and requires approximately 1.7 GB of VRAM at 8 k context. For systems with 2 GB or more VRAM, NVFP4 is recommended. If VRAM is limited, consider using a different quantization not provided here.

What GPU do you need for NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (1.2 GB file, about 1.7 GB in use).

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters833M
Layers6
Trained context1,048,576 tokens
KV cache (fp16)6 KB per token

Frequently asked questions about NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash

How much VRAM does NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash need?

About 1.7 GB at its main file with an 8K context window. That is the 1.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash on an 8 GB GPU?

Yes, with the smaller files: the 1.2 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash GGUF?

It depends on the quant: file is 1.2 GB.

What context length does NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.2 GB at 32K.

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

The files are on Hugging Face in the magnitudedev/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 DFlash use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the NVFP4 quantization requires about 1.7 GB at 8 k context, leaving ample headroom for 8 GB VRAM.

Does this model support vision tasks?

No, the model only accepts text input and does not provide vision capabilities.

What license applies to this model?

Use is governed by the OpenMDW‑1.1 model license.

Other GGUFs of NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash

Similar models

Browse all →

More from magnitudedev

All by magnitudedev →

More Nemotron models

All Nemotron →

Other tiny models

All tiny models →