breeze-tts-2 needs about 4.3 GB of memory at Q8_0 (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.2 GB (Q4_K) to 5.7 GB (F16).
Breeze TTS 2 – real‑time, bilingual text‑to‑speech
Breeze TTS 2 is an open‑weight text‑to‑speech model that supports real‑time interaction in English and Chinese. It offers voice clone, voice design, and voice direction capabilities with ultra‑low latency and streaming performance.
Good at
- Real‑time streaming
- Voice clone with reference audio
- Voice design from natural language
Limits
- Requires at least 12 GB GPU for eager inference
- No vision support
- Non‑commercial use only
Best for
- Real‑time voice assistants
- Interactive storytelling
- Custom voice creation
Who it’s for. Developers building real‑time TTS applications who need bilingual support and low latency. Researchers exploring open‑weight TTS models for non‑commercial projects.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.3 GB | Fits | Get file → | |
| F16 | 5.7 GB | 6.9 GB | Fits | Get file → |
For 12 GB GPU use Q4_K (2.21 GB, 3 GB memory at 8k context). For 24 GB GPU use Q8_0 (3.43 GB, 4.3 GB memory). F16 (5.71 GB, 6.9 GB memory) requires more VRAM.
What GPU do you need for breeze-tts-2?
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 Q4_K (2.2 GB file, about 3.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 4.3 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.7 GB file, about 6.9 GB in use).
Which breeze-tts-2 quant should you choose?
Q8_0 (3.4 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_K at 2.2 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 breeze-tts-2
How much VRAM does breeze-tts-2 need?
About 4.3 GB at Q8_0 with an 8K context window. That is the 3.4 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 breeze-tts-2 on an 8 GB GPU?
Yes, with F16: 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 breeze-tts-2 GGUF?
It depends on the quant: Q4_K is 2.2 GB, Q8_0 is 3.4 GB, F16 is 5.7 GB.
Where can I download breeze-tts-2 GGUF?
The files are on Hugging Face in the cstr/breeze-tts-2-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 breeze-tts-2 use?
Hugging Face lists the license as other. 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 Breeze TTS 2 on 8 GB VRAM?
No, the minimum recommended VRAM is 12 GB for eager inference.
Is the model licensed for commercial use?
No, the weights are licensed for research and non‑commercial use only.
Does the model support voice cloning without a reference?
Voice cloning requires reference audio with its transcript; voice design is available without reference.