kugelaudio 0 open needs about 9.2 GB of memory at Q6_K (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.7 GB (Q4_K) to 17.3 GB (F16).
7B parameter text‑to‑speech model for European languages
kugelaudio 0 open is a 7B parameter TTS model based on the VibeVoice architecture. It supports 23 European languages and outputs 24 kHz mono PCM audio. The model is released under an MIT license.
Good at
- European language coverage
- High‑quality voice synthesis
- Supports multiple speaking styles
Limits
- No vision support
- Requires pre‑encoded voice embeddings
- No encoder weights included
Best for
- Generating synthetic speech for multilingual apps
- Voice cloning with pre‑encoded embeddings
- Creating TTS datasets for research
Who it’s for. Developers and researchers building multilingual TTS solutions. The model is suitable for projects that need open‑source, European‑language voice synthesis without the need for raw audio encoder training.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q6_K | 7.8 GB | 9.2 GB | Too big | Get file → | |
| F16 | 17.3 GB | 19.9 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K quantized file (5.71 GB, ~6.9 GB memory at 8k context). If more VRAM is available, Q6_K (7.79 GB, ~9.2 GB memory) offers higher precision. The full F16 file (17.29 GB, ~19.9 GB memory) requires substantial memory and is best for high‑accuracy inference.
What GPU do you need for kugelaudio 0 open?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q4_K (5.7 GB file, about 6.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.8 GB file, about 9.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (7.8 GB file, about 9.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (17.3 GB file, about 19.9 GB in use).
Which kugelaudio 0 open quant should you choose?
Q6_K (7.8 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 Q4_K at 5.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kugelaudio 0 open
How much VRAM does kugelaudio 0 open need?
About 9.2 GB at Q6_K with an 8K context window. That is the 7.8 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 kugelaudio 0 open on an 8 GB GPU?
Yes, with Q4_K: the 5.7 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kugelaudio 0 open GGUF?
It depends on the quant: Q4_K is 5.7 GB, Q6_K is 7.8 GB, F16 is 17.3 GB.
Where can I download kugelaudio 0 open GGUF?
The files are on Hugging Face in the cstr/kugelaudio-0-open-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 kugelaudio 0 open 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 kugelaudio 0 open on 8 GB VRAM?
Yes, the Q4_K quantized file is 5.71 GB and requires about 6.9 GB of VRAM at 8k context, fitting within an 8 GB GPU.
Does the model support voice cloning from raw audio?
No, the released GGUF files omit encoder weights; only pre‑encoded voice embeddings are supported.
What languages are supported?
The model supports 23 European languages including en, de, fr, es, it, pt, nl, pl, ru, uk, cs, ro, hu, sv, da, fi, no, el, bg, sk, hr, sr, tr.