NE

NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4

NemotronGGUF by julianmbUpdated 2026-08-22
Download on Hugging Face
Parameters31.6B
Context256K
Layers52
Architecturenemotron_h_moe
Smallest quant16.8 GB
Quick answer

NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4 needs about 24.4 GB of memory at its main file (a 16.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 16.8 GB to 18.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4 is a 31.6B-parameter Nemotron model in GGUF format, quantized by julianmb. Its trained context length is 256K tokens. The repository has 3 quant files, from 16.8 GB to 18.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—16.8 GB 24.3 GB
Too big Get file →
—16.9 GB 24.4 GB
Too big Get file →
—18.0 GB 25.5 GB
Too big Get file →

What GPU do you need for NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is the main file (18.0 GB file, about 25.5 GB in use).

Which NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 16.8 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters31.6B (approximate, mixture of experts)
Active parameters3B
Layers52
Trained context262,144 tokens
KV cache (fp16)832 KB per token

Frequently asked questions about NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4

How much VRAM does NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4 need?

About 24.4 GB at its main file with an 8K context window. That is the 16.9 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 ROCmFP4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4 GGUF?

It depends on the quant: file is 16.8 GB, file is 16.9 GB, file is 18.0 GB.

What context length does NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 7.0 GB at 8K and 27.9 GB at 32K.

Where can I download NVIDIA Nemotron 3.5 Lightning 30B A3B ROCmFP4 GGUF?

The files are on Hugging Face in the julianmb/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-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 ROCmFP4 use?

Hugging Face lists the license as openmdw-1.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from julianmb

All by julianmb →

More Nemotron models

All Nemotron →

Other medium models

All medium models →