XTTS v2 GPT needs about 0.8 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 8 quants, from 0.1 GB (F16) to 1.7 GB.
XTTS v2 GPT – a 0.434 B parameter text‑to‑speech model
XTTS v2 GPT is a 0.434 B parameter model designed for text‑to‑speech synthesis. It is available in multiple GGUF quantizations and is licensed under MPL‑2.0. The model can be used with audio.cpp for speech generation.
Good at
- Text‑to‑speech synthesis
- Low‑memory inference
- Mature quantization options
Limits
- No vision support
- Requires 8 k context for estimates
- License is MPL‑2.0
Best for
- Generating synthetic speech for apps
- Creating voice‑over content
- Testing TTS pipelines
Who it’s for. Developers and researchers needing a compact TTS model for local inference. The model is suitable for projects that require a small footprint and open‑source licensing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| — | 1.7 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_M (≈0.29 GB file, ≈0.8 GB memory). For 4 GB VRAM, use Q4_0 or Q4_K_M. For 2 GB VRAM, use Q4_0 or Q4_K_M. For 1 GB VRAM, use Q4_0 or Q4_K_M. For 512 MB VRAM, use Q4_0 or Q4_K_M. For 256 MB VRAM, use Q4_0 or Q4_K_M. For 128 MB VRAM, use Q4_0 or Q4_K_M. For 64 MB VRAM, use Q4_0 or Q4_K_M. For 32 MB VRAM, use Q4_0 or Q4_K_M. For 16 MB VRAM, use Q4_0 or Q4_K_M. For 8 MB VRAM, use Q4_0 or Q4_K_M. For 4 MB VRAM, use Q4_0 or Q4_K_M. For 2 MB VRAM, use Q4_0 or Q4_K_M. For 1 MB VRAM, use Q4_0
What GPU do you need for XTTS v2 GPT?
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 (1.7 GB file, about 2.4 GB in use).
Which XTTS v2 GPT quant should you choose?
Q4_K_M is the usual starting point for XTTS v2 GPT: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is F16 at 0.1 GB, with the quality trade-offs that come with fewer bits. 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 XTTS v2 GPT
How much VRAM does XTTS v2 GPT need?
About 0.8 GB at Q4_K_M 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 XTTS v2 GPT on an 8 GB GPU?
Yes, with the smaller files: the 1.7 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of XTTS v2 GPT GGUF?
It depends on the quant: F16 is 0.1 GB, F16 is 0.1 GB, F16 is 0.1 GB, F16 is 0.1 GB, Q4_0 is 0.3 GB, Q4_K_M is 0.3 GB and 2 more.
Where can I download XTTS v2 GPT GGUF?
The files are on Hugging Face in the onicubag/xTTSv2-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 XTTS v2 GPT use?
Hugging Face lists the license as mpl-2.0. 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 XTTS v2 GPT on 8 GB VRAM?
Yes, the Q4_0 or Q4_K_M quantizations use about 0.8 GB of VRAM at 8 k context, which fits within 8 GB.
Does XTTS v2 GPT support multiple languages?
The model does not specify supported languages in the provided data.
Is XTTS v2 GPT free to use?
Yes, it is licensed under MPL‑2.0, which allows free use and modification.