Breeze-TTS-2 needs about 4.2 GB of memory at Q8_0 (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 2.5 GB (Q4_K) to 6.3 GB (F16).
Breeze-TTS-2: lightweight, real‑time bilingual text‑to‑speech
Breeze‑TTS‑2 is a 3.01‑billion‑parameter model for real‑time English and Chinese TTS. It supports voice clone, voice design, and voice direction with ultra‑low latency. The model runs on NVIDIA, AMD, and Intel GPUs via Breeze‑TTS‑2.cpp.
Good at
- Real‑time streaming at 0.32 RTF on RTX 3060
- Ultra‑low latency TTFA under 40 ms on H100
- Supports vocal events and bilingual speech
Limits
- Requires at least 12 GB GPU for eager inference
- No vision support
- License restricts commercial use
Best for
- Real‑time voice assistants
- Interactive storytelling
- Voice‑over production
Who it’s for. Engineers and researchers building real‑time TTS applications who need a lightweight, bilingual model. The model is suitable for non‑commercial projects and research use only.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q4_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 3.1 GB | 3.9 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 4.3 GB | Fits | Get file → | |
| Q8_0 | 3.6 GB | 4.5 GB | Fits | Get file → | |
| F16 | 6.3 GB | 7.5 GB | Tight | Get file → |
For 12 GB GPU, Q4_K files (~2.5 GB) use ~3.3 GB VRAM at 8 k context. Q6_K (~3.1 GB) uses ~3.9 GB VRAM. For 24 GB GPU, Q8_0 (~3.3 GB) uses ~4.2 GB VRAM. F16 (~6.3 GB) uses ~7.5 GB 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 Q6_K (3.1 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.3 GB file, about 7.5 GB in use).
Which Breeze-TTS-2 quant should you choose?
Q8_0 (3.3 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 2.5 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 4.2 GB at Q8_0 with an 8K context window. That is the 3.3 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 Breeze-TTS-2 on an 8 GB GPU?
Yes, with F16: the 6.3 GB file needs about 7.5 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 2.5 GB, Q4_K is 2.5 GB, Q6_K is 3.1 GB, Q8_0 is 3.3 GB, Q8_0 is 3.4 GB, Q8_0 is 3.6 GB and 1 more.
Where can I download Breeze-TTS-2 GGUF?
The files are on Hugging Face in the HoppouAI/Breeze-TTS-2.cpp 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 an RTX 3060?
Yes, the Q8_0 quantization runs at about 1.2× realtime on an RTX 3060 with ~4 GB VRAM.
Does the model support voice cloning with reference audio?
Yes, it clones voice from reference audio with the exact transcript to preserve timbre and style.
Is the model free for commercial use?
No, the license allows research and non‑commercial use only.