ZONOS2 needs about 7.0 GB of memory at Q5_K (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 0.0 GB to 15.3 GB (F16).
ZONOS2 – high‑fidelity multilingual text‑to‑speech model
ZONOS2 is a text‑to‑speech model trained on more than 6 million hours of multilingual speech. It delivers expressiveness and quality comparable to top TTS providers with low latency. The model uses an ECAPA‑TDNN speaker encoder, a MoE backbone, and a DAC vocoder.
Good at
- High‑fidelity voice cloning
- Multilingual speech synthesis
- Low‑latency inference
Limits
- Requires NVIDIA GPU with CUDA
- Linux x86_64 only
- No vision support
Best for
- Creating realistic synthetic voices
- Generating multilingual audio content
- Voice‑clone applications
Who it’s for. Developers and researchers needing a high‑quality TTS engine for multilingual use cases. The model is suitable for local deployment on systems with NVIDIA GPUs and CUDA support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_K | 4.9 GB | 6.0 GB | Fits | Get file → | |
| Q5_K | 5.8 GB | 7.0 GB | Fits | Get file → | |
| Q6_K | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → | |
| F16 | 15.3 GB | 17.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K (file size 4.92 GB, memory 6 GB). For 12 GB VRAM, Q5_K (5.82 GB, 7 GB) or Q6_K (6.79 GB, 8.1 GB). For 16 GB VRAM, Q8_0 (8.54 GB, 10.1 GB) provides the best quality. All quants keep the spine at F16.
What GPU do you need for ZONOS2?
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 (0.3 GB file, about 0.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K (4.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K (5.8 GB file, about 7.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.3 GB file, about 17.7 GB in use).
Which ZONOS2 quant should you choose?
Q5_K (5.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ZONOS2
How much VRAM does ZONOS2 need?
About 7.0 GB at Q5_K with an 8K context window. That is the 5.8 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 ZONOS2 on an 8 GB GPU?
Yes, with Q5_K: the 5.8 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ZONOS2 GGUF?
It depends on the quant: file is 0.0 GB, file is 0.3 GB, Q4_K is 4.9 GB, Q5_K is 5.8 GB, Q6_K is 6.8 GB, Q8_0 is 8.5 GB and 1 more.
Where can I download ZONOS2 GGUF?
The files are on Hugging Face in the Zyphra/ZONOS2-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 ZONOS2 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 ZONOS2 on 8 GB VRAM?
Yes, the Q4_K quant requires approximately 6 GB of VRAM at 8 k context.
Does ZONOS2 support languages other than English?
The model was trained on multilingual speech, but language support details are not specified.
Is there a hosted version of ZONOS2?
Yes, a hosted version is available at cloud.zyphra.com/audio-playground.