HO

HOT Step CPP SuperSep

HotGGUF by scragnogUpdated 2026-07-28
Download on Hugging Face
Parameters67M
Context—
Layers—
Architecturebs-roformer
Smallest quant0.3 GB
Quick answer

HOT Step CPP SuperSep needs about 1.0 GB of memory at F32 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.3 GB (F32) to 0.9 GB (F32).

HOT Step CPP SuperSep – ONNX stem separation model

HOT Step CPP SuperSep is a 0.0668B bs-roformer model for multi‑stem audio separation. It runs natively via ONNX Runtime GPU with no Python required. The model is distributed in FP32 precision.

Good at

  • Fast GPU inference
  • Spectrogram‑based separation
  • Standalone ONNX deployment

Limits

  • No vision support
  • Requires ONNX Runtime 1.25.1+
  • MIT license only

Best for

  • Music source separation
  • Podcast audio cleanup
  • Live performance isolation

Who it’s for. Developers building audio processing pipelines who need a lightweight, GPU‑accelerated stem separation model. The model is suitable for integration into C++ applications via the SuperSep engine.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F320.3 GB 0.8 GB
Fits Get file →
F320.3 GB 0.8 GB
Fits Get file →
F320.4 GB 1.0 GB
Fits Get file →
F320.7 GB 1.3 GB
Fits Get file →
F320.9 GB 1.5 GB
Fits Get file →

All available GGUF files are FP32. The smallest file is 0.27 GB and needs about 0.8 GB VRAM at 8 k context. The largest is 0.91 GB and needs about 1.5 GB VRAM. Choose the 0.27 GB file for 8 GB VRAM or the 0.44 GB file for 12 GB VRAM. Estimates are approximate.

What GPU do you need for HOT Step CPP SuperSep?

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: the best quant that fits is F32 (0.9 GB file, about 1.5 GB in use).

Which HOT Step CPP SuperSep quant should you choose?

F32 (0.4 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is F32 at 0.3 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebs-roformer
Parameters67M

Source

Quantized byscragnog
FamilyHot
Licensemit
Downloads (HF)1,304
Last updated2026-07-28

Frequently asked questions about HOT Step CPP SuperSep

How much VRAM does HOT Step CPP SuperSep need?

About 1.0 GB at F32 with an 8K context window. That is the 0.4 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 HOT Step CPP SuperSep on an 8 GB GPU?

Yes, with F32: the 0.9 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of HOT Step CPP SuperSep GGUF?

It depends on the quant: F32 is 0.3 GB, F32 is 0.3 GB, F32 is 0.4 GB, F32 is 0.7 GB, F32 is 0.9 GB.

Where can I download HOT Step CPP SuperSep GGUF?

The files are on Hugging Face in the scragnog/HOT-Step-CPP-SuperSep repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does HOT Step CPP SuperSep use?

Hugging Face lists the license as mit. 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?

Yes, the 0.27 GB FP32 file requires about 0.8 GB VRAM at 8 k context, well within an 8 GB GPU.

Does this model support vision tasks?

No, it is designed solely for audio stem separation.

What license does this model use?

The model is released under the MIT license.

Similar models

Browse all →

More from scragnog

All by scragnog →

More Hot models

All Hot →

Other tiny models

All tiny models →