NE

NVIDIA Nemotron 3.5 Lightning 30B A3B MagicQuant

NemotronGGUF by lmcolemanUpdated 2026-08-20
Download on Hugging Face
Parameters32.9B
Context1024K
Layers53
Architecturenemotron_h_moe
Smallest quant18.9 GB
Quick answer

NVIDIA Nemotron 3.5 Lightning 30B A3B MagicQuant needs about 26.5 GB of memory at Q4_K_M (a 18.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 18.9 GB (Q4_K_M) to 25.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.

NVIDIA Nemotron 3.5 Lightning 30B A3B MagicQuant is a 32.9B-parameter Nemotron model in GGUF format, quantized by lmcoleman. Its trained context length is 1024K tokens. The repository has 3 quant files, from 18.9 GB (Q4_K_M) to 25.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M18.9 GB 26.5 GB
Too big Get file →
Q5_K_M22.1 GB 29.7 GB
Too big Get file →
Q6_K25.9 GB 33.5 GB
Too big Get file →

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

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 Q5_K_M (22.1 GB file, about 29.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (25.9 GB file, about 33.5 GB in use).

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

Q4_K_M is the usual starting point for NVIDIA Nemotron 3.5 Lightning 30B A3B MagicQuant: it balances file size and quality well. Here it is a 18.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters32.9B (approximate, mixture of experts)
Active parameters3B
Layers53
Trained context1,048,576 tokens
KV cache (fp16)848 KB per token

Source

Quantized bylmcoleman
FamilyNemotron
Licenseother
Downloads (HF)239
Last updated2026-08-20

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

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

About 26.5 GB at Q4_K_M with an 8K context window. That is the 18.9 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 MagicQuant on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.5 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q4_K_M is 18.9 GB, Q5_K_M is 22.1 GB, Q6_K is 25.9 GB.

What context length does NVIDIA Nemotron 3.5 Lightning 30B A3B MagicQuant 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 7.1 GB at 8K and 28.5 GB at 32K.

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

The files are on Hugging Face in the lmcoleman/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MagicQuant-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 MagicQuant 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.

Other GGUFs of NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16

Similar models

Browse all →

More from lmcoleman

All by lmcoleman →

More Nemotron models

All Nemotron →

Other medium models

All medium models →