NE

Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q4 K M

NemotronGGUF by mlasliUpdated 2026-08-17
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant24.5 GB
Quick answer

Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q4 K M needs about 32.0 GB of memory at Q4_K_M (a 24.5 GB file) with an 8K context window, so it fits on a 32 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 Q4_K_M GGUF

Nemotron 3.5 Lightning 30B A3B Heretic Uncensored is a 31.6B parameter model with 3B active parameters. It uses a hybrid nemotron_h_moe architecture and is quantized to Q4_K_M for local inference with llama.cpp. The model supports a context length of 1,048,576 tokens.

Good at

  • Roleplay
  • Large context handling
  • Hybrid MoE architecture

Limits

  • Requires llama.cpp build b10326+
  • 24.52 GB file size
  • 32 GB VRAM at 8k context

Best for

  • Long‑form dialogue
  • Custom agent development
  • Local inference on high‑VRAM GPUs

Who it’s for. Developers and researchers who need a large, hybrid MoE model for local deployment. The model is suitable for building specialized AI agents and for use cases that require extensive context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M24.5 GB 32.0 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M which requires 32 GB VRAM at 8k context; this is the only quant available. For larger VRAM budgets the same quant can be used, but memory usage scales with context length. The 24.52 GB file can be loaded on systems with sufficient storage.

What GPU do you need for Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q4 K M?

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_M (24.5 GB file, about 32.0 GB in use).

Which Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q4 K M quant should you choose?

Q4_K_M is the usual starting point for Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q4 K M: it balances file size and quality well. Here it is a 24.5 GB file.

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)3,676
Last updated2026-08-17

Frequently asked questions about Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q4 K M

How much VRAM does Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q4 K M need?

About 32.0 GB at Q4_K_M with an 8K context window. That is the 24.5 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 Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.0 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 Q4 K M GGUF?

It depends on the quant: Q4_K_M is 24.5 GB.

What context length does Nemotron 3.5 Lightning 30B A3B Heretic Uncensored Q4 K M 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 Q4 K M GGUF?

The files are on Hugging Face in the mlasli/Nemotron-3.5-Lightning-30B-A3B-Heretic-Uncensored-Q4_K_M-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 Q4 K M 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 Q4_K_M quant requires 32 GB VRAM at 8k context, so 8 GB VRAM is insufficient.

What build of llama.cpp is required?

A build of llama.cpp b10326 or newer is required to run the nemotron_h_moe architecture.

Does the model support vision?

No, the model has no vision capabilities.

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 →