VI

VieNeu-TTS-v3-Turbo

VieneuGGUF by phuocnguyen90Updated 2026-07-21
Download on Hugging Face
Parameters146M
Context—
Layers—
Architectureaudiocpp
Smallest quant0.2 GB
Quick answer

VieNeu-TTS-v3-Turbo needs about 0.7 GB of memory at its main file (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.

VieNeu-TTS v3 Turbo – 48 kHz Vietnamese TTS in a single 163 MB GGUF file

VieNeu‑TTS v3 Turbo delivers 48 kHz high‑fidelity speech with 23 preset voices across North, Central and South Vietnamese regions. The model is trained from scratch on ~10 000 hours of English‑Vietnamese speech and runs torch‑free on CPU via ONNX Runtime or on CUDA via audio.cpp.

Good at

  • 48 kHz high‑fidelity Vietnamese TTS
  • Real‑time streaming with 16 concurrent streams on RTX 3060
  • OpenAI‑compatible API and Docker support

Limits

  • No vision support
  • No license information provided
  • Requires 163 MB GGUF file

Best for

  • Voice cloning in Vietnamese
  • Real‑time TTS in web or mobile apps
  • Bilingual (En–Vi) code‑switching

Who it’s for. Developers building Vietnamese TTS solutions who need a compact, torch‑free model for CPU or a CUDA‑accelerated stream on consumer GPUs. The model is suitable for applications that require instant load times and low memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 0.7 GB
Fits Get file →

The single available GGUF file is 163 MB. It can be loaded on any system with at least 1 GB of RAM. For lower memory budgets, no other quantizations are provided, so use the 163 MB file as is.

What GPU do you need for VieNeu-TTS-v3-Turbo?

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 (0.2 GB file, about 0.7 GB in use).

Specifications

Architecture from the GGUF header

Architectureaudiocpp
Parameters146M

Source

Quantized byphuocnguyen90
FamilyVieneu
Downloads (HF)38,694
Last updated2026-07-21

Frequently asked questions about VieNeu-TTS-v3-Turbo

How much VRAM does VieNeu-TTS-v3-Turbo need?

About 0.7 GB at its main file 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 VieNeu-TTS-v3-Turbo on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of VieNeu-TTS-v3-Turbo GGUF?

It depends on the quant: file is 0.2 GB.

Where can I download VieNeu-TTS-v3-Turbo GGUF?

The files are on Hugging Face in the phuocnguyen90/VieNeu-TTS-v3-Turbo-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run VieNeu‑TTS v3 Turbo on a CPU with 1 GB RAM?

Yes, the 163 MB GGUF file loads on a CPU with 1 GB RAM, using ONNX Runtime for inference.

Does the model support GPU streaming?

Yes, on a CUDA machine it auto‑switches to the PyTorch engine with continuous‑batching stream scheduler, achieving 16 concurrent streams on an RTX 3060.

Is there a license for this model?

The model card does not specify a license; use it only if you comply with the original authors’ terms.

Other GGUFs of VieNeu-TTS-v3-Turbo

Similar models

Browse all →

More Vieneu models

All Vieneu →

Other tiny models

All tiny models →