SO

Soofi S Instruct Preview

SoofiGGUF by Soofi-ProjectUpdated 2026-07-17
Download on Hugging Face
Parameters31.6B
Context1024K
Layers—
Architecturenemotron_h_moe
Smallest quant26.0 GB
Quick answer

Soofi S Instruct Preview needs about 38.1 GB of memory at Q8_0 (a 33.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 26.0 GB (Q5_K_M) to 63.2 GB.

Soofi S Instruct Preview is a 31.6B-parameter Soofi model in GGUF format, quantized by Soofi-Project. Its trained context length is 1024K tokens. The repository has 3 quant files, from 26.0 GB (Q5_K_M) to 63.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M26.0 GB 29.7 GB
Too big Get file →
Q8_033.6 GB 38.1 GB
Too big Get file →
—63.2 GB 71.3 GB
Too big Get file →

What GPU do you need for Soofi S Instruct Preview?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q5_K_M (26.0 GB file, about 29.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (33.6 GB file, about 38.1 GB in use).

Which Soofi S Instruct Preview quant should you choose?

Q8_0 (33.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q5_K_M at 26.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters31.6B
Trained context1,048,576 tokens

Source

Quantized bySoofi-Project
FamilySoofi
Licenseother
Downloads (HF)14
Last updated2026-07-17

Frequently asked questions about Soofi S Instruct Preview

How much VRAM does Soofi S Instruct Preview need?

About 38.1 GB at Q8_0 with an 8K context window. That is the 33.6 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 Soofi S Instruct Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Soofi S Instruct Preview GGUF?

It depends on the quant: Q5_K_M is 26.0 GB, Q8_0 is 33.6 GB, file is 63.2 GB.

What context length does Soofi S Instruct Preview support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download Soofi S Instruct Preview GGUF?

The files are on Hugging Face in the Soofi-Project/Soofi-S-Instruct-Preview-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 Soofi S Instruct Preview 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 from Soofi-Project

All by Soofi-Project →

More Soofi models

All Soofi →

Other medium models

All medium models →