RE USE needs about 0.5 GB of memory at F32 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.
RE-USE: Universal Speech Enhancement in F32
RE-USE is a lightweight speech enhancement model with 0.00961 billion parameters. It restores degraded speech while preserving sample rate and linguistic content. The model is available in a single F32 GGUF file.
Good at
- Restoring noisy speech
- Preserving speaker identity
- Handling multiple sampling rates
Limits
- Only F32 quantization available
- No vision support
- Requires GPU for inference
Best for
- Audio post‑processing
- Noise reduction in recordings
- Speech enhancement in research
Who it’s for. Researchers and developers needing a small, language‑agnostic speech enhancement model. The model is for research and development only and is released under the NVIDIA One‑Way Noncommercial License.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F32 | 0.0 GB | 0.5 GB | Fits | Get file → |
The only available quant is F32, file size 0.04 GB. Estimated VRAM usage at 8 k context is 0.5 GB. This is suitable for GPUs with at least 1 GB VRAM. No other quantizations are provided.
What GPU do you need for RE USE?
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 (0.0 GB file, about 0.5 GB in use).
Which RE USE quant should you choose?
F32 (0.0 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about RE USE
How much VRAM does RE USE need?
About 0.5 GB at F32 with an 8K context window. That is the 0.0 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 RE USE on an 8 GB GPU?
Yes, with F32: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of RE USE GGUF?
It depends on the quant: F32 is 0.0 GB.
Where can I download RE USE GGUF?
The files are on Hugging Face in the audio-cpp/RE-USE-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 RE USE 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 RE-USE on a GPU with 1 GB VRAM?
Yes, the F32 model uses about 0.5 GB VRAM at 8 k context, so a 1 GB GPU can handle it.
Does RE-USE support image input?
No, RE-USE is a speech enhancement model and does not support vision.
Is there a quantized version for lower VRAM?
Only the F32 quantization is provided; no lower‑precision variants exist.