demodokos foundry tts v4 needs about 3.6 GB of memory at its main file (a 2.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.0 GB to 3.9 GB.
Demodokos Foundry TTS v4 – local text‑to‑speech model
Demodokos Foundry TTS v4 is a 0.909 billion‑parameter model based on the qwen3_tts architecture. It supports 10 speech languages and offers expressive narration with line‑by‑line emotion control. The model is available in multiple GGUF quantizations for local deployment.
Good at
- Expressive multi‑language speech
- Emotion control per line
- Voice cloning from short samples
Limits
- No vision support
- License type is other
- No trained context tokens specified
Best for
- Voiceover production
- Multilingual narration
- Audio workflow automation
Who it’s for. The model is aimed at creators who need private, local AI voice solutions. It is suitable for YouTubers, podcasters, and audio engineers who prefer to keep data on their own GPU.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.4 GB | 0.9 GB | Fits | Get file → | |
| — | 1.4 GB | 2.1 GB | Fits | Get file → | |
| — | 2.8 GB | 3.6 GB | Fits | Get file → | |
| — | 2.8 GB | 3.7 GB | Fits | Get file → | |
| — | 3.8 GB | 4.8 GB | Fits | Get file → | |
| — | 3.9 GB | 4.8 GB | Fits | Get file → |
For a 4 GB VRAM GPU, the 0.02 GB file uses about 0.5 GB memory at 8 k context. A 0.36 GB file uses about 0.9 GB memory. For 8 GB VRAM, the 1.41 GB file uses about 2.1 GB memory, and the 2.8 GB file uses about 3.6 GB memory. Choose the smallest file that meets your quality needs.
What GPU do you need for demodokos foundry tts v4?
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 the main file (2.8 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (3.9 GB file, about 4.8 GB in use).
Which demodokos foundry tts v4 quant should you choose?
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 demodokos foundry tts v4
How much VRAM does demodokos foundry tts v4 need?
About 3.6 GB at its main file with an 8K context window. That is the 2.8 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 demodokos foundry tts v4 on an 8 GB GPU?
Yes, with the smaller files: the 3.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of demodokos foundry tts v4 GGUF?
It depends on the quant: file is 0.0 GB, file is 0.4 GB, file is 1.4 GB, file is 2.8 GB, file is 2.8 GB, file is 3.8 GB and 1 more.
Where can I download demodokos foundry tts v4 GGUF?
The files are on Hugging Face in the cmp-nct/demodokos-foundry-tts-v4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does demodokos foundry tts v4 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 Demodokos Foundry TTS v4 on 4 GB VRAM?
Yes, the 0.02 GB and 0.36 GB GGUF files use 0.5 GB and 0.9 GB memory respectively at 8 k context, fitting within 4 GB VRAM.
Does this model support voice cloning?
Yes, it includes voice cloning from short samples as part of its speech capabilities.
What languages are supported for speech?
The model supports 10 speech languages, as listed in its feature set.