NE

Nemotron 3.5 Lightning 30B A3B CRACK

NemotronGGUF by dealignaiUpdated 2026-08-12
Download on Hugging Face
Parameters32.9B
Context1024K
Layers53
Architecturenemotron_h_moe
Smallest quant18.7 GB
Quick answer

Nemotron 3.5 Lightning 30B A3B CRACK 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 3 quants, from 18.7 GB (Q2_K) to 35.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.

Nemotron 3.5 Lightning 30B A3B CRACK – GGUF quantized for llama.cpp

Nemotron 3.5 Lightning 30B A3B CRACK is a 32.9B parameter model with 3B active parameters. It uses a hybrid nemotron_h_moe architecture with Mamba‑2, MoE and attention layers. The model is available in three GGUF quantizations: Q2_K, Q4_K_M and Q8_0.

Good at

  • Reasoning and thinking
  • Tool usage
  • Large context handling

Limits

  • No vision support
  • License is other
  • No safety guardrails

Best for

  • Custom LLM fine‑tuning
  • Research prototypes
  • Low‑latency inference

Who it’s for. Developers and researchers who need a large, mixture‑of‑experts model for custom applications. The model is suitable for those who can manage the memory requirements and are comfortable with the reduced safety guardrails.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K18.7 GB 26.3 GB
Too big Get file →
Q4_K_M25.4 GB 33.0 GB
Too big Get file →
Q8_035.0 GB 42.6 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 18.66 GB, estimated memory 26.3 GB at 8 k context). For 12 GB VRAM, Q4_K_M (25.43 GB, 33 GB). For 16 GB or more, Q8_0 (35 GB, 42.6 GB). The estimates are approximate.

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

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 Q2_K (18.7 GB file, about 26.3 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 Nemotron 3.5 Lightning 30B A3B CRACK quant should you choose?

Q4_K_M is the usual starting point for Nemotron 3.5 Lightning 30B A3B CRACK: 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 Q2_K at 18.7 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 bydealignai
FamilyNemotron
Licenseother
Downloads (HF)523
Last updated2026-08-12

Frequently asked questions about Nemotron 3.5 Lightning 30B A3B CRACK

How much VRAM does Nemotron 3.5 Lightning 30B A3B CRACK 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 Nemotron 3.5 Lightning 30B A3B CRACK on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.3 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q2_K is 18.7 GB, Q4_K_M is 25.4 GB, Q8_0 is 35.0 GB.

What context length does Nemotron 3.5 Lightning 30B A3B CRACK 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 Nemotron 3.5 Lightning 30B A3B CRACK GGUF?

The files are on Hugging Face in the dealignai/Nemotron-3.5-Lightning-30B-A3B-CRACK-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 CRACK 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?

The Q2_K quantization requires about 26.3 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The license is listed as other; review the repository for details.

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

Similar models

Browse all →

More from dealignai

All by dealignai →

More Nemotron models

All Nemotron →

Other medium models

All medium models →