VieNeu-TTS-v3-Turbo-staging 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 2 quants, from 0.2 GB (Q8_0) to 0.3 GB (BF16).
VieNeu-TTS v3 Turbo – 48 kHz Vietnamese TTS with 23 preset voices
VieNeu‑TTS v3 Turbo delivers 48 kHz high‑fidelity speech in Vietnamese. It supports 23 preset voices across North, Central, and South regions, instant voice cloning, real‑time streaming, and bilingual En–Vi code‑switching. The model runs on CPU via ONNX Runtime or on CUDA with automatic batching.
Good at
- 48 kHz high‑fidelity Vietnamese TTS
- Real‑time streaming with 16 concurrent streams on RTX 3060
- Instant voice cloning and LoRA fine‑tuning
Limits
- No vision support
- Requires GPU for optimal streaming
- License is Apache‑2.0
Best for
- Developers building Vietnamese TTS services
- Voice cloning applications
- Real‑time audio streaming APIs
Who it’s for. Engineers and researchers needing a Vietnamese TTS model with high audio quality and real‑time streaming. The model is suitable for applications that require multiple preset voices and instant voice cloning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| BF16 | 0.3 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, use the Q8_0 quantized file (0.19 GB, ~0.7 GB memory at 8k context). If more VRAM is available, the BF16 file (0.29 GB, ~0.8 GB memory) offers slightly higher precision. Memory estimates are approximate.
What GPU do you need for VieNeu-TTS-v3-Turbo-staging?
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 BF16 (0.3 GB file, about 0.8 GB in use).
Which VieNeu-TTS-v3-Turbo-staging 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about VieNeu-TTS-v3-Turbo-staging
How much VRAM does VieNeu-TTS-v3-Turbo-staging 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 VieNeu-TTS-v3-Turbo-staging on an 8 GB GPU?
Yes, with BF16: the 0.3 GB file needs about 0.8 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-staging GGUF?
It depends on the quant: Q8_0 is 0.2 GB, BF16 is 0.3 GB.
Where can I download VieNeu-TTS-v3-Turbo-staging GGUF?
The files are on Hugging Face in the pnnbao-ump/VieNeu-TTS-v3-Turbo repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does VieNeu-TTS-v3-Turbo-staging use?
Hugging Face lists the license as apache-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 VieNeu‑TTS v3 Turbo on 8 GB VRAM?
Yes, the Q8_0 quantized file is 0.19 GB and requires about 0.7 GB memory at 8k context, fitting comfortably in 8 GB VRAM.
Does the model support GPU streaming?
Yes, on CUDA it supports continuous batching with up to 16 concurrent streams on an RTX 3060.
Is the model licensed for commercial use?
The model is released under the Apache‑2.0 license, which permits commercial use.