ZE

ZeroTTS

ZerottsGGUF by zeroweight-aiUpdated 2026-09-06
Download on Hugging Face
Parameters202M
Context—
Layers—
Architecturezerotts
Smallest quant0.1 GB
Quick answer

ZeroTTS needs about 0.7 GB of memory at Q8_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q4_0) to 0.8 GB (F32).

ZeroTTS – a compact Vietnamese TTS model in GGUF format

ZeroTTS is a 0.202 billion‑parameter TTS model repackaged for ggml runtime. It delivers ultra‑natural Vietnamese speech with zero‑shot voice cloning and real‑time CPU inference. The GGUF files are 4× smaller than ONNX weights.

Good at

  • Ultra‑natural Vietnamese TTS
  • Zero‑shot voice cloning from 3–30 s audio
  • Real‑time CPU streaming

Limits

  • No vision support
  • No GPU acceleration required
  • No per‑speaker fine‑tuning

Best for

  • Local Vietnamese TTS on laptops
  • Voice cloning for short audio clips
  • Real‑time speech synthesis in browsers

Who it’s for. Developers needing a lightweight Vietnamese TTS solution for local or browser deployment. Ideal for projects that require quick voice cloning without GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.1 GB 0.6 GB
Fits Get file →
Q8_00.2 GB 0.7 GB
Fits Get file →
F320.8 GB 1.4 GB
Fits Get file →

For 8 GB VRAM, the Q4_0 file (0.13 GB) uses 0.6 GB at 8k context. Q8_0 (0.22 GB) uses 0.7 GB. If more precision is needed, use F32 (0.81 GB) which requires 1.4 GB. All estimates are approximate.

What GPU do you need for ZeroTTS?

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 F32 (0.8 GB file, about 1.4 GB in use).

Which ZeroTTS quant should you choose?

Q8_0 (0.2 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.

If memory is tight, the smallest file is Q4_0 at 0.1 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

Architecturezerotts
Parameters202M

Source

Quantized byzeroweight-ai
FamilyZerotts
Licensemit
Downloads (HF)748
Last updated2026-09-06

Frequently asked questions about ZeroTTS

How much VRAM does ZeroTTS need?

About 0.7 GB at Q8_0 with an 8K context window. That is the 0.2 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 ZeroTTS on an 8 GB GPU?

Yes, with F32: the 0.8 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ZeroTTS GGUF?

It depends on the quant: Q4_0 is 0.1 GB, Q8_0 is 0.2 GB, F32 is 0.8 GB.

Where can I download ZeroTTS GGUF?

The files are on Hugging Face in the zeroweight-ai/ZeroTTS-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 ZeroTTS 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 ZeroTTS on a laptop CPU?

Yes, it runs real‑time on a laptop CPU with no GPU required.

What is the smallest file I can use?

The Q4_0 quantized file is 0.13 GB and uses about 0.6 GB of VRAM at 8k context.

Does ZeroTTS support other languages?

It is built for Vietnamese, including tones and code‑switched English.

Similar models

Browse all →

More Zerotts models

All Zerotts →

Other tiny models

All tiny models →