NE

Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K

NemotronGGUF by mlasliUpdated 2026-08-17
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant33.5 GB
Quick answer

Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K needs about 41.0 GB of memory at Q6_K (a 33.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6_K GGUF

Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6_K is a 31.6B parameter model with 3B active parameters. It uses a hybrid nemotron_h_moe architecture with Mamba-2, MoE, and Attention layers. The model is quantized to Q6_K and available as a 33.51 GB GGUF file.

Good at

  • Reasoning
  • Roleplay
  • Tool usage

Limits

  • No vision support
  • Requires llama.cpp build b10326+
  • License is other

Best for

  • Custom LLM fine‑tuning
  • Local inference on high‑VRAM GPUs
  • Building specialized AI agents

Who it’s for. Developers and researchers who need a large, mixture‑of‑experts model for fine‑tuning or local deployment. The model is ready for commercial use and can be integrated into custom pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K33.5 GB 41.0 GB
Too big Get file →

For 8 GB VRAM, the Q6_K quantization is too large; it requires about 41 GB at 8 k context. For 16 GB VRAM, the same quantization is still too large. The only available quant is Q6_K, so a higher‑VRAM machine is needed.

What GPU do you need for Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q6_K (33.5 GB file, about 41.0 GB in use).

Which Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K quant should you choose?

Q6_K (33.5 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

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 bymlasli
FamilyNemotron
Licenseother
Downloads (HF)758
Last updated2026-08-17

Frequently asked questions about Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K

How much VRAM does Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K need?

About 41.0 GB at Q6_K with an 8K context window. That is the 33.5 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 Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 41.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K GGUF?

It depends on the quant: Q6_K is 33.5 GB.

What context length does Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K 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 Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K GGUF?

The files are on Hugging Face in the mlasli/Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-Q6_K-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 Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q6 K 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?

No. The Q6_K quantization requires about 41 GB of VRAM at 8 k context, which exceeds 8 GB.

What llama.cpp build is required?

The model requires a llama.cpp build b10326 or newer.

Is the model safe for commercial use?

Yes, the model is ready for commercial use but has no safety alignment due to abliterated safety.

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

Similar models

Browse all →

More from mlasli

All by mlasli →

More Nemotron models

All Nemotron →

Other medium models

All medium models →