NE

Nemotron Cascade 2 30B A3B

NemotronGGUF by bartowskiUpdated 2026-03-22
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant0.1 GB
Quick answer

Nemotron Cascade 2 30B A3B needs about 32.2 GB of memory at Q4_K_M (a 24.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 28 quants, from 0.1 GB to 63.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

Nemotron Cascade 2 30B A3B – a 30B MoE model with 3B active parameters

Nemotron Cascade 2 30B A3B is a 30B parameter mixture‑of‑experts model with 3B active parameters. It excels at reasoning tasks and can operate in both thinking and instruct modes. The model is available in multiple GGUF quantizations.

Good at

  • Strong reasoning
  • Agentic capabilities
  • Large context handling

Limits

  • Requires high VRAM for full precision
  • No vision support
  • License is other

Best for

  • Math problem solving
  • Code reasoning
  • Long‑form text generation

Who it’s for. Developers and researchers who need a large reasoning‑capable model for local inference. The model is suitable for users with sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 7.5 GB
Tight Get file →
IQ2_XXS18.1 GB 25.6 GB
Too big Get file →
IQ2_XS18.1 GB 25.6 GB
Too big Get file →
IQ2_S18.1 GB 25.6 GB
Too big Get file →
IQ2_M18.1 GB 25.6 GB
Too big Get file →
Q2_K18.2 GB 25.6 GB
Too big Get file →
IQ4_XS18.2 GB 25.6 GB
Too big Get file →
IQ4_NL18.2 GB 25.7 GB
Too big Get file →
Q3_K_S18.2 GB 25.7 GB
Too big Get file →
Q4_018.3 GB 25.8 GB
Too big Get file →
Q2_K_L18.3 GB 25.8 GB
Too big Get file →
IQ3_XXS19.0 GB 26.5 GB
Too big Get file →
IQ3_XS19.1 GB 26.5 GB
Too big Get file →
Q3_K_M19.1 GB 26.5 GB
Too big Get file →
Q3_K_L19.5 GB 27.0 GB
Too big Get file →
IQ3_M19.5 GB 27.0 GB
Too big Get file →
Q3_K_XL19.7 GB 27.2 GB
Too big Get file →
Q4_120.1 GB 27.6 GB
Too big Get file →
Q4_K_S22.4 GB 29.9 GB
Too big Get file →
Q5_K_S24.0 GB 31.5 GB
Too big Get file →
Q4_K_M24.7 GB 32.2 GB
Too big Get file →
Q4_K_L24.9 GB 32.3 GB
Too big Get file →
Q5_K_M26.2 GB 33.7 GB
Too big Get file →
Q5_K_L26.3 GB 33.8 GB
Too big Get file →
Q6_K33.6 GB 41.0 GB
Too big Get file →
Q6_K_L33.6 GB 41.0 GB
Too big Get file →
Q8_033.6 GB 41.1 GB
Too big Get file →
BF1663.2 GB (2 parts) 70.7 GB
Too big Get file →

For 8‑GB VRAM, use Q4_0 (18.27 GB file, ~25.8 GB VRAM at 8k context). For 12‑GB VRAM, Q4_K_S (22.45 GB file, ~29.9 GB VRAM). For 16‑GB VRAM, Q5_K_S (24.01 GB file, ~31.5 GB VRAM). Estimates are approximate.

What GPU do you need for Nemotron Cascade 2 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: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_S (24.0 GB file, about 31.5 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 Nemotron Cascade 2 30B A3B quant should you choose?

Q4_K_M is the usual starting point for Nemotron Cascade 2 30B A3B: it balances file size and quality well. Here it is a 24.7 GB file.

The Q8_0 file is 33.6 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

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 bybartowski
FamilyNemotron
Licenseother
Downloads (HF)7,496
Last updated2026-03-22

Frequently asked questions about Nemotron Cascade 2 30B A3B

How much VRAM does Nemotron Cascade 2 30B A3B need?

About 32.2 GB at Q4_K_M with an 8K context window. That is the 24.7 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 Cascade 2 30B A3B on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nemotron Cascade 2 30B A3B GGUF?

It depends on the quant: file is 0.1 GB, IQ2_XXS is 18.1 GB, IQ2_XS is 18.1 GB, IQ2_S is 18.1 GB, IQ2_M is 18.1 GB, Q2_K is 18.2 GB and 22 more.

What context length does Nemotron Cascade 2 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 Nemotron Cascade 2 30B A3B GGUF?

The files are on Hugging Face in the bartowski/nvidia_Nemotron-Cascade-2-30B-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 Nemotron Cascade 2 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 Nemotron Cascade 2 30B A3B on 8 GB VRAM?

Only the Q4_0 quantization can fit within 8 GB VRAM, but it still requires ~25.8 GB VRAM at 8k context, so it is not feasible on 8 GB VRAM.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What is the maximum context length?

The model was trained with 1,048,576 tokens of context.

Other GGUFs of Nemotron-Cascade-2-30B-A3B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Nemotron models

All Nemotron →

Other medium models

All medium models →