Sidon needs about 0.8 GB of memory at Q6_K (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 0.5 GB (F16).
Sidon: a small speech‑restoration model in GGUF format
Sidon is a 0.00127‑billion‑parameter model for removing noise and reverberation from speech. It upsamples 16 kHz input to 48 kHz output. The model is released under the MIT license.
Good at
- Speech denoising
- Reverberation removal
- Bandwidth upsampling
Limits
- No vision support
- Small context only
- Requires CrispASR for inference
Best for
- Audio post‑processing
- Podcast cleanup
- Voice‑over enhancement
Who it’s for. Developers and researchers needing lightweight speech restoration. The model is suitable for edge devices and low‑resource environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| F16 | 0.5 GB | 1.1 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K (0.25 GB file, 0.8 GB memory at 8k context) is recommended. Q6_K and Q8_0 offer similar memory usage with slightly higher precision. F16 provides the highest precision but needs 1.1 GB memory.
What GPU do you need for Sidon?
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 F16 (0.5 GB file, about 1.1 GB in use).
Which Sidon quant should you choose?
Q6_K (0.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
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
Source
Frequently asked questions about Sidon
How much VRAM does Sidon need?
About 0.8 GB at Q6_K with an 8K context window. That is the 0.3 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 Sidon on an 8 GB GPU?
Yes, with F16: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sidon GGUF?
It depends on the quant: file is 0.0 GB, Q4_K is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.3 GB, F16 is 0.5 GB.
Where can I download Sidon GGUF?
The files are on Hugging Face in the cstr/Sidon-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 Sidon 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 Sidon on 8 GB VRAM?
Yes, the Q4_K quantization uses 0.8 GB memory at 8k context, fitting comfortably in 8 GB VRAM.
Does Sidon support GPU inference?
It works with CrispASR builds that support integer dot product; GPUs like GTX 1660 SUPER may need the latest CrispASR version.