NE

NVIDIA Nemotron 3.5 Lightning 30B A3B

NemotronGGUF by vcruz305Updated 2026-08-11
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant9.8 GB
Quick answer

NVIDIA Nemotron 3.5 Lightning 30B A3B needs about 25.5 GB of memory at MXFP4_MOE (a 18.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 7 quants, from 9.8 GB (Q2_0) to 33.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

32‑billion‑parameter Nemotron 3.5 Lightning 30B A3B with MoE

NVIDIA Nemotron 3.5 Lightning 30B A3B is a 32‑billion‑parameter LLM using a hybrid Mamba‑2 and MoE architecture. It contains 3 billion active parameters and supports up to 1,048,576 context tokens. The model is released under the OpenMDW‑1.1 license and is ready for commercial use.

Good at

  • Large context handling
  • Mixture‑of‑Experts efficiency
  • High‑capacity inference

Limits

  • Requires 8‑GB+ VRAM for full offload
  • Large memory footprint for 8‑k context
  • No vision or multimodal support

Best for

  • Long‑form content generation
  • Domain‑specific fine‑tuning
  • High‑throughput inference on GPUs

Who it’s for. Engineers and researchers building specialized AI agents who need a large, efficient LLM with MoE capabilities. The model is suitable for commercial deployment and custom fine‑tuning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_09.8 GB 17.2 GB
Too big Get file →
Q2_011.7 GB 19.2 GB
Too big Get file →
IQ4_NL18.0 GB 25.5 GB
Too big Get file →
MXFP4_MOE18.0 GB 25.5 GB
Too big Get file →
Q4_018.1 GB 25.5 GB
Too big Get file →
Q5_022.0 GB 29.4 GB
Too big Get file →
Q8_033.6 GB 41.1 GB
Too big Get file →

For 8 GB VRAM, use the Q2_0 quant (9.76 GB file, ~17.2 GB memory at 8 k context). For 12 GB VRAM, Q2_0 (11.74 GB) or Q4_0 (18.06 GB) are viable. For 24 GB VRAM, choose Q5_0 (21.96 GB) or MXFP4_MOE (17.98 GB) for better context headroom. Memory estimates are approximate.

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

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: the best quant that fits is Q2_0 (11.7 GB file, about 19.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_0 (22.0 GB file, about 29.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (33.6 GB file, about 41.1 GB in use).

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

MXFP4_MOE (18.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is Q2_0 at 9.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized byvcruz305
FamilyNemotron
Licenseother
Downloads (HF)1,374
Last updated2026-08-11

Frequently asked questions about NVIDIA Nemotron 3.5 Lightning 30B A3B

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

About 25.5 GB at MXFP4_MOE with an 8K context window. That is the 18.0 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.2 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q2_0 is 9.8 GB, Q2_0 is 11.7 GB, IQ4_NL is 18.0 GB, MXFP4_MOE is 18.0 GB, Q4_0 is 18.1 GB, Q5_0 is 22.0 GB and 1 more.

What context length does NVIDIA Nemotron 3.5 Lightning 30B A3B 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 7.0 GB at 8K and 27.9 GB at 32K.

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

The files are on Hugging Face in the vcruz305/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-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 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, with the Q2_0 quant (9.76 GB file). It will require offloading layers to system RAM and may need reduced context length.

Does the model support vision or multimodal inputs?

No, the model is purely text‑based and does not include vision capabilities.

What is the maximum context length?

The model supports up to 1,048,576 tokens, but practical limits depend on VRAM and KV‑cache settings.

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

Similar models

Browse all →

More from vcruz305

All by vcruz305 →

More Nemotron models

All Nemotron →

Other medium models

All medium models →