NE

Nemotron-3-Super-64B-A12B-Math-REAP

NemotronGGUF by Max-and-OmnisUpdated 2026-04-24
Download on Hugging Face
Parameters64.3B
Context1024K
Layers88
Architecturenemotron_h_moe
Smallest quant39.9 GB
Quick answer

Nemotron-3-Super-64B-A12B-Math-REAP needs about 67.9 GB of memory at Q4_K_M (a 55.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 39.9 GB (IQ2_M) to 128.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 47.2 GB.

Nemotron-3-Super-64B-A12B-Math-REAP is a 64.3B-parameter Nemotron model in GGUF format, quantized by Max-and-Omnis. Its trained context length is 1024K tokens. The repository has 7 quant files, from 39.9 GB (IQ2_M) to 128.6 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M39.9 GB 52.2 GB
Too big Get file →
IQ3_M43.4 GB 55.7 GB
Too big Get file →
IQ4_XS45.9 GB 58.2 GB
Too big Get file →
Q4_K_M55.6 GB 67.9 GB
Too big Get file →
Q6_K68.3 GB 80.6 GB
Too big Get file →
Q8_075.3 GB 87.6 GB
Too big Get file →
BF16128.6 GB 140.9 GB
Too big Get file →

What GPU do you need for Nemotron-3-Super-64B-A12B-Math-REAP?

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: no quant fits at an 8K context.

Which Nemotron-3-Super-64B-A12B-Math-REAP quant should you choose?

Q4_K_M is the usual starting point for Nemotron-3-Super-64B-A12B-Math-REAP: it balances file size and quality well. Here it is a 55.6 GB file.

The Q8_0 file is 75.3 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 IQ2_M at 39.9 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
Parameters64.3B (approximate, mixture of experts)
Active parameters12B
Layers88
Trained context1,048,576 tokens
KV cache (fp16)1408 KB per token

Source

Quantized byMax-and-Omnis
FamilyNemotron
Licenseother
Downloads (HF)287
Last updated2026-04-24

Frequently asked questions about Nemotron-3-Super-64B-A12B-Math-REAP

How much VRAM does Nemotron-3-Super-64B-A12B-Math-REAP need?

About 67.9 GB at Q4_K_M with an 8K context window. That is the 55.6 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-Super-64B-A12B-Math-REAP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 52.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nemotron-3-Super-64B-A12B-Math-REAP GGUF?

It depends on the quant: IQ2_M is 39.9 GB, IQ3_M is 43.4 GB, IQ4_XS is 45.9 GB, Q4_K_M is 55.6 GB, Q6_K is 68.3 GB, Q8_0 is 75.3 GB and 1 more.

What context length does Nemotron-3-Super-64B-A12B-Math-REAP 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 11.8 GB at 8K and 47.2 GB at 32K.

Where can I download Nemotron-3-Super-64B-A12B-Math-REAP GGUF?

The files are on Hugging Face in the Max-and-Omnis/Nemotron-3-Super-64B-A12B-Math-REAP-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-Super-64B-A12B-Math-REAP 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.

Similar models

Browse all →

More Nemotron models

All Nemotron →

Other large models

All large models →