NE

NVIDIA Nemotron 3.5 Lightning 30B A3B

NemotronGGUF by NANI-NithinUpdated 2026-08-11
Download on Hugging Face
Parameters32.9B
Context1024K
Layers53
Architecturenemotron_h_moe
Smallest quant17.9 GB
Quick answer

NVIDIA Nemotron 3.5 Lightning 30B A3B needs about 33.0 GB of memory at Q4_K_M (a 25.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 17.9 GB (IQ1_S) to 65.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.

NVIDIA Nemotron 3.5 Lightning 30B A3B – a 30B parameter Mixture‑of‑Experts LLM

NVIDIA Nemotron 3.5 Lightning 30B A3B is a 30B parameter model with 3B active parameters. It uses a hybrid nemotron_h_moe architecture with interleaved Mamba‑2, MoE, and attention layers. The model is released under Apache‑2.0 and supports local inference via GGUF.

Good at

  • Large context handling
  • Mixture‑of‑Experts efficiency
  • Fast local inference with GGUF

Limits

  • Requires Mixture‑of‑Experts aware runtime
  • No vision support
  • Large VRAM needed for higher quants

Best for

  • Customizing domain‑specific agents
  • Fine‑tuning on specialized datasets
  • Deploying on high‑end GPUs

Who it’s for. Engineers and researchers building specialized AI agents who need a large, efficient LLM. The model is suitable for commercial use and can be fine‑tuned or distilled.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S17.9 GB 25.5 GB
Too big Get file →
IQ2_XXS17.9 GB 25.5 GB
Too big Get file →
IQ2_S18.6 GB 26.3 GB
Too big Get file →
IQ2_M18.6 GB 26.3 GB
Too big Get file →
Q2_K18.7 GB 26.3 GB
Too big Get file →
IQ3_XXS18.7 GB 26.3 GB
Too big Get file →
Q3_K_S18.7 GB 26.3 GB
Too big Get file →
IQ3_S18.7 GB 26.3 GB
Too big Get file →
IQ4_XS18.7 GB 26.3 GB
Too big Get file →
Q4_018.7 GB 26.3 GB
Too big Get file →
IQ4_NL18.7 GB 26.3 GB
Too big Get file →
IQ3_M18.9 GB 26.5 GB
Too big Get file →
Q3_K_M20.7 GB 28.3 GB
Too big Get file →
Q3_K_L21.6 GB 29.2 GB
Too big Get file →
Q5_022.8 GB 30.4 GB
Too big Get file →
Q4_K_S22.8 GB 30.4 GB
Too big Get file →
Q5_K_S24.8 GB 32.4 GB
Too big Get file →
Q4_K_M25.4 GB 33.0 GB
Too big Get file →
Q5_K_M27.0 GB 34.7 GB
Too big Get file →
Q6_K34.9 GB 42.5 GB
Too big Get file →
Q8_035.0 GB 42.6 GB
Too big Get file →
F1665.9 GB 73.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 22.84 GB, estimated 30.4 GB memory). For 16 GB VRAM, Q5_K_S (24.81 GB, 32.4 GB memory) is a good balance. For 32 GB VRAM, Q6_K (34.92 GB, 42.5 GB memory) provides higher precision.

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_K_S (22.8 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.0 GB file, about 42.6 GB in use).

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

Q4_K_M is the usual starting point for NVIDIA Nemotron 3.5 Lightning 30B A3B: it balances file size and quality well. Here it is a 25.4 GB file.

The Q8_0 file is 35.0 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 17.9 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
Parameters32.9B (approximate, mixture of experts)
Active parameters3B
Layers53
Trained context1,048,576 tokens
KV cache (fp16)848 KB per token

Source

Quantized byNANI-Nithin
FamilyNemotron
Licenseapache-2.0
Downloads (HF)3,046
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 33.0 GB at Q4_K_M with an 8K context window. That is the 25.4 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 25.5 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ1_S is 17.9 GB, IQ2_XXS is 17.9 GB, IQ2_S is 18.6 GB, IQ2_M is 18.6 GB, Q2_K is 18.7 GB, IQ3_XXS is 18.7 GB and 16 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 7.1 GB at 8K and 28.5 GB at 32K.

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

The files are on Hugging Face in the NANI-Nithin/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 apache-2.0. 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?

Use the Q4_K_M quant, which requires about 30.4 GB memory at 8 k context. It will not fit on 8 GB VRAM, so a smaller quant is needed.

Is this model licensed for commercial use?

Yes, it is released under the Apache‑2.0 license and is suitable for commercial applications.

Does the model support vision inputs?

No, the model has no vision capabilities and is text‑only.

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

Similar models

Browse all →

More from NANI-Nithin

All by NANI-Nithin →

More Nemotron models

All Nemotron →

Other medium models

All medium models →