ST

HOT Step CPP StableStep

StableGGUF by scragnogUpdated 2026-10-22
Download on Hugging Face
Parameters1.45B
Context—
Layers—
Architecturesa3-dit
Smallest quant0.0 GB
Quick answer

HOT Step CPP StableStep needs about 1.4 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 33 quants, from 0.0 GB to 2.9 GB (BF16).

HOT Step CPP StableStep – local AI music post‑processing

HOT Step CPP StableStep is a local post‑processing model for music generation. It re‑renders instrumentals via Stable Audio 3 and cleans vocals, preserving original mixes. The model is a converted derivative of stabilityai/stable‑audio‑3‑medium.

Good at

  • Instrumental re‑rendering
  • Vocal separation and remix
  • Spectral detail enhancement

Limits

  • No vision support
  • Requires Stable Step CPP app
  • License limits commercial use for large orgs

Best for

  • Local music remixing
  • Post‑processing generated tracks
  • Audio detail restoration

Who it’s for. Users of the HOT‑Step‑CPP music generation app who need high‑quality post‑processing. It is suitable for musicians, producers, and hobbyists working locally.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
IQ1_S0.3 GB 0.8 GB
Fits Get file →
IQ1_M0.3 GB 0.9 GB
Fits Get file →
IQ2_XXS0.4 GB 0.9 GB
Fits Get file →
IQ2_XS0.4 GB 1.0 GB
Fits Get file →
Q2_K0.5 GB 1.1 GB
Fits Get file →
Q2_K0.5 GB 1.1 GB
Fits Get file →
IQ3_XXS0.6 GB 1.1 GB
Fits Get file →
Q3_K_L0.6 GB 1.2 GB
Fits Get file →
Q3_K_M0.6 GB 1.2 GB
Fits Get file →
Q3_K_S0.6 GB 1.2 GB
Fits Get file →
Q3_K_L0.6 GB 1.2 GB
Fits Get file →
Q3_K_M0.6 GB 1.2 GB
Fits Get file →
Q3_K_S0.6 GB 1.2 GB
Fits Get file →
MXFP40.8 GB 1.4 GB
Fits Get file →
IQ4_XS0.8 GB 1.4 GB
Fits Get file →
—0.8 GB 1.4 GB
Fits Get file →
Q4_K_M0.8 GB 1.4 GB
Fits Get file →
Q4_K_S0.8 GB 1.4 GB
Fits Get file →
Q4_K_M0.8 GB 1.4 GB
Fits Get file →
Q4_K_S0.8 GB 1.4 GB
Fits Get file →
F160.9 GB 1.5 GB
Fits Get file →
F160.9 GB 1.5 GB
Fits Get file →
Q5_K_M1.0 GB 1.6 GB
Fits Get file →
Q5_K_S1.0 GB 1.6 GB
Fits Get file →
Q5_K_M1.0 GB 1.6 GB
Fits Get file →
Q5_K_S1.0 GB 1.6 GB
Fits Get file →
BF161.2 GB 1.8 GB
Fits Get file →
Q6_K1.2 GB 1.9 GB
Fits Get file →
Q6_K1.2 GB 1.9 GB
Fits Get file →
Q8_01.6 GB 2.2 GB
Fits Get file →
Q8_01.6 GB 2.2 GB
Fits Get file →
BF162.9 GB 3.8 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (0.3 GB) or IQ1_M (0.34 GB). For 12 GB VRAM, Q2_K (0.5 GB) or Q3_K_M (0.64 GB) are good choices. For 16 GB VRAM, Q4_K_M (0.83 GB) or F16 (0.85 GB) provide higher precision. Estimates are approximate.

What GPU do you need for HOT Step CPP StableStep?

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 BF16 (2.9 GB file, about 3.8 GB in use).

Which HOT Step CPP StableStep quant should you choose?

Q4_K_M is the usual starting point for HOT Step CPP StableStep: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.6 GB, about 1.9 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 0.0 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

Architecturesa3-dit
Parameters1.45B

Source

Quantized byscragnog
FamilyStable
Licenseother
Downloads (HF)1,199
Last updated2026-10-22

Frequently asked questions about HOT Step CPP StableStep

How much VRAM does HOT Step CPP StableStep need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.8 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 StableStep on an 8 GB GPU?

Yes, with BF16: the 2.9 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, Q2_K is 0.5 GB and 27 more.

Where can I download HOT Step CPP StableStep GGUF?

The files are on Hugging Face in the scragnog/HOT-Step-CPP-StableStep 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 StableStep 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?

Yes, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM with estimated memory usage of 0.8–0.9 GB at 8k context.

Does this model support image generation?

No, it is a music post‑processing model and has no vision capabilities.

What license applies to this model?

It is distributed under the Stability AI Community License, free for research and non‑commercial use, with restrictions for large organizations.

Other GGUFs of stable-audio-3-medium

Similar models

Browse all →

More from scragnog

All by scragnog →

More Stable models

All Stable →

Other tiny models

All tiny models →