chatterbox nano needs about 1.2 GB of memory at Q8_0 (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.6 GB (Q8_0) to 0.9 GB (F16).
Chatterbox Nano – lightweight 110M‑parameter TTS model in GGUF format
Chatterbox Nano is a 110M‑parameter text‑to‑speech model converted to GGUF for audio.cpp. It supports voice cloning and native paralinguistic tags. The model is released under the MIT license.
Good at
- Fast CPU inference – 3× faster than realtime on 8 cores
- High‑fidelity voice cloning
- Native paralinguistic tags such as [cough] and [laugh]
Limits
- No vision support
- Limited to 8 k context length
- Requires audio.cpp v0.9.0‑jv.3 or later
Best for
- Low‑latency voice agents
- Narration and creative audio workflows
- Voice cloning from short reference clips
Who it’s for. Developers building TTS applications or voice agents who need a small, efficient model that runs on CPU. The model is suitable for hobbyists and production use where low latency and high audio quality are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| F16 | 0.9 GB | 1.5 GB | Fits | Get file → |
For 8 GB VRAM use the Q8_0 quant, which is 0.62 GB and needs about 1.2 GB of VRAM at 8 k context. If you have 4 GB VRAM, the F16 quant (0.89 GB, 1.5 GB VRAM) is still feasible but will use more memory. These estimates are approximate.
What GPU do you need for chatterbox nano?
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 F16 (0.9 GB file, about 1.5 GB in use).
Which chatterbox nano quant should you choose?
Q8_0 (0.6 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 chatterbox nano
How much VRAM does chatterbox nano need?
About 1.2 GB at Q8_0 with an 8K context window. That is the 0.6 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 chatterbox nano on an 8 GB GPU?
Yes, with F16: the 0.9 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of chatterbox nano GGUF?
It depends on the quant: Q8_0 is 0.6 GB, F16 is 0.9 GB.
Where can I download chatterbox nano GGUF?
The files are on Hugging Face in the delebash/chatterbox-nano-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 chatterbox nano use?
Hugging Face lists the license as mit. 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 Chatterbox Nano on 8 GB VRAM?
Yes, the Q8_0 quant is 0.62 GB and requires about 1.2 GB of VRAM at 8 k context, well within 8 GB.
Does Chatterbox Nano support voice cloning?
Yes, it includes a voice encoder and can clone a voice from a reference clip longer than 5 seconds.
What license does Chatterbox Nano have?
The model is released under the MIT license.