yovoice model needs about 0.8 GB of memory at Q8_0 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU.
yovoice Kokoro-82M 1.1-zh Q8_0 – 103 built‑in voices for Chinese and English TTS
The yovoice Kokoro-82M 1.1-zh Q8_0 model offers 103 built‑in voices, including 100 Chinese and 3 English voices. It runs with audio.cpp and does not require Python at inference. The model supports Chinese, American English, and British English in an experimental mode.
Good at
- Fast inference with 0.26 GB file size
- Built‑in Chinese pronunciation tables
- No reference audio needed
Limits
- No voice cloning support
- Experimental English support
- License terms require review
Best for
- Local TTS on low‑resource devices
- Rapid voice prototyping
- Chinese language applications
Who it’s for. Developers needing a lightweight TTS model with many Chinese voices and a few English options. Suitable for embedded systems or local inference where Python is unavailable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → |
The only available quant is Q8_0, 0.26 GB file size and ~0.8 GB VRAM at 8 k context. It fits on GPUs with 1 GB VRAM or more. No other quants are provided, so use Q8_0 for any memory budget above 1 GB.
What GPU do you need for yovoice model?
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 Q8_0 (0.3 GB file, about 0.8 GB in use).
Which yovoice model quant should you choose?
Q8_0 (0.3 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about yovoice model
How much VRAM does yovoice model need?
About 0.8 GB at Q8_0 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 yovoice model on an 8 GB GPU?
Yes, with Q8_0: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of yovoice model GGUF?
It depends on the quant: Q8_0 is 0.3 GB.
Where can I download yovoice model GGUF?
The files are on Hugging Face in the leemysw/yovoice-model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does yovoice model 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 yovoice Kokoro-82M 1.1-zh Q8_0 on 1 GB VRAM?
Yes, the model requires about 0.8 GB VRAM at 8 k context, so 1 GB VRAM is sufficient.
Does this model support voice cloning?
No, the model does not support reference audio or voice cloning.
Which languages are supported?
Chinese, American English, and British English (experimental).